TLDR: A shift from Powell to Warsh signals a move toward tighter, more preemptive Fed policy, with direct implications for rates, asset prices, and portfolio positioning.

As Jerome Powell’s time as Chair of the Federal Reserve comes to an end on May 15, the anticipated confirmation of nominee, former Fed Governor Kevin Warsh, marks more than a standard leadership change at the Federal Reserve.

It signals a potential shift in how rates are determined and executed. Both Powell and Warsh are nominees of President Donald J. Trump but it is unclear what type of Chair Warsh will be should the Senate confirm his nomination.

Although a Senate Banking Committee confirmation is expected in the coming weeks, a paved path does not lie ahead of Warsh. It is anticipated that he will face rigorous questions on central bank digital currencies (CBDCs), federal debt, and how he will maintain Fed independence coming off of Powell’s term that reflected an administration that hurled insults and launched a federal investigation when Powell did not lower rates.

Is Warsh still a “Hawk”?

Kevin Warsh previously served on the Federal Reserve Board of Governors from Feb. 24, 2006, to March 31, 2011 during the financial crisis of 2008 and remains a long-standing critic of the Fed’s post-crisis policy record.

Warsh acted as the bank’s primary liaison to Wall Street and as the Fed’s representative to the Group of Twenty (G20). His career began as Special Assistant to former President George W. Bush at the White House. Bush’s nomination of Warsh drew criticism as he was the youngest appointment in the history of the Fed.

The difference between Powell’s framework and what a Warsh-led Fed could look like is not theoretical. It shows up clearly in how inflation, rates, and policy responses have evolved in recent years.

This dynamic helps explain why a shift toward a more preemptive Fed would represent a meaningful change in how markets interpret policy signals.

From “Flexible” to “Reform”

Powell’s Fed embraced flexibility. Under Powell’s leadership, the central bank formally shifted to an average inflation targeting framework, allowing inflation to run above 2% for some time following periods of undershooting. This framework justified patience in tightening, even as inflation began to accelerate in 2021.

Warsh, by contrast, has consistently warned about the long-term costs of easy money, particularly on its impact on financial stability and asset prices. If he brings that philosophy to the chair, the Fed could move toward a more preemptive posture: quicker to tighten, less tolerant of inflation overshoots, and more focused on maintaining credibility with markets.

In practical terms, that could mean:

• Potentially Higher Rates: Warsh’s Fed may have lower tolerance for upward inflationary pressure

• Likely More Positive Real Rates: Greater emphasis on real rates (the policy rate after inflation) staying positive

• More Opaque: Less reliance on forward guidance as a policy tool

Balance Sheet Policy Back in Focus

Another likely shift is the role of the Fed’s balance sheet. Powell oversaw an era of massive expansion, first through quantitative easing and later through emergency liquidity facilities.

Warsh has been openly critical of the Fed’s footprint in financial markets. His leadership could accelerate balance sheet normalization, both in pace and in principle. The Fed might become more reluctant to intervene in market functioning unless absolutely necessary, raising the bar for future liquidity programs.

That has implications not just for rates, but for risk assets broadly. A smaller, less active Fed balance sheet typically translates into tighter financial conditions, even absent explicit rate hikes.

Perhaps the most immediate change would come in how the Fed communicates.

Powell evolved into a highly transparent chair, using press conferences, speeches, and clear forward guidance to shape market expectations. This approach reduced volatility at times, but also risked locking the Fed into specific policy paths.

Warsh is likely to favor more ambiguity. Historically, he has argued that excessive transparency can weaken policy effectiveness by encouraging markets to front-run the Fed. A shift in this direction could reintroduce uncertainty, and with it, volatility, into rate markets.

Political Economy and Institutional Tension

“That is up to the President,” Treasure Scott Bessent responded when asked if Warsh would be sued by the U.S. Justice Department for not cutting interest rates at the President’s direction.

Warsh’s nomination would also land in a different political environment than the one Powell navigated. Questions about central bank independence, fiscal dominance, and the Fed’s role in inequality and asset prices are now more prominent.

Unlike Powell, who often positioned himself as a pragmatic consensus-builder, Warsh may face sharper scrutiny from both sides:

• Critics wary of tighter policy slowing growth

• Others concerned about the Fed’s past tolerance for inflation

This could make the Fed’s policy path more contested, even if the underlying economic data is similar.

Unprecedented Volatility

The Trump administration has reflected an historically volatile stock market continuously threatened by government shutdowns, geopolitical events, and the looming potential threat of an AI bubble burst.

If Warsh is confirmed, the key question is not whether policy changes, but how quickly.

Three signals will matter most:

1. The reaction function: Does the Fed respond faster to inflation data than under Powell?

2. Balance sheet guidance: Is there a clear commitment to shrinking the Fed’s footprint?

3. Communication style: Does the Fed reduce forward guidance and tolerate more market uncertainty?

The answers will shape everything from the yield curve to equity valuations.

Is AI in a Bubble? Our thoughts here.

A Regime Shift, Not Just a Personnel Change

Leadership transitions at the Fed rarely produce immediate, dramatic shifts. Institutional inertia is real, and the broader FOMC will still shape decisions.

But the chair sets the tone.

Powell’s legacy will likely be defined by flexibility, crisis responsiveness, and a willingness to stretch the Fed’s toolkit. A Warsh era would point in a different direction: toward restraint, preemption, and a narrower interpretation of the Fed’s role.

If that shift materializes, markets may need to adjust not just to a new chair,but rather to a new regime and investors may need to rethink assumptions that have held for over a decade. Such as that the Fed will step in quickly, that liquidity will follow stress, and that policy will err on the side of support. A more preemptive Fed changes both the timing and direction of those expectations.

Warsh’s Biggest Challenge

History suggests that the market rarely gives a new Fed Chair a grace period. Instead, it tests them. Within roughly the first year of their tenure, each modern Chair has been forced to respond to a defining episode of financial stress: Black Monday under Alan Greenspan, the onset of the Global Financial Crisis under Ben Bernanke, the 2015–2016 stock market selloff often associated with the “flash crash” environment early in Janet Yellen’s term, and the pandemic shock of COVID-19 pandemic under Jerome Powell. If confirmed, Warsh is unlikely to be an exception. The combination of elevated inflation, geopolitical instability, and stretched asset valuations suggests that his credibility, and policy framework, may be stress-tested early, forcing him to balance market stabilization with his instinct toward tighter, more disciplined monetary policy.

What This Means for You

I have been consistently counseling our Atlas Analytics clients on this emerging regime for months and writing about this shift in the macroeconomic environment here for weeks.

With Warsh’s appointment, inflation remaining sticky, and geopolitical pressures building in the Middle East, our view has been that rates are unlikely to fall and may move higher.

Importantly, this is not a reactive view. Our GDP forecasting framework began signaling this shift earlier in the year, well before it became more widely discussed.

Recent positioning, including pressure on long-duration assets and strength in the dollar, has been consistent with that signal. The takeaway is not the trade itself, but the ability to identify inflection points early and translate them into actionable decisions.

As we move into what could be a fundamentally different rate environment, both opportunity and risk are expanding quickly. We will continue to share our views and positioning in real time. For those looking to stay ahead of these shifts rather than react to them, we’d welcome a conversation about how Atlas Analytics can support your investment process.

Get in Touch

This article was written with valuable research assistance from Morgan Reppert, Executive Operations Associate for Atlas Analytics.

The most important economic decision the Federal Reserve makes is whether to hold, raise, or lower interest rates.

Over the past few months, we have seen direct tension between President Donald Trump and Fed Chair Jerome Powell over whether rates should be cut.

Last week, Powell announced a unanimous vote to keep rates steady between 3.5% and 3.75%, while signaling a possible cut later this year:

“The forecast is that we will be making progress on inflation, not as much as we had hoped, but some progress.”

Powell’s term as Fed Chair ends this May, though he has stated he will remain in his role until Fed Chair nominee, Kevin Warsh is confirmed. Powell’s term on the Board of Governors runs through 2028, though he has indicated he will not step down until the ongoing Justice Department probe is resolved.

This tension is not new. It is rooted in how the role of the Fed Chair and the Federal Reserve was designed.

The History of the Chair of the Federal Reserve

The role of the Fed Chair was established by the Banking Act of 1935. Since then, there have been 10 chairs. Most had prior government experience, and many served within the Federal Reserve system before being appointed. The position was designed to centralize authority and strengthen the Fed’s ability to respond to economic crises.

The Chair serves a four-year term, while members of the Board of Governors serve staggered 14-year terms. This structure is specifically designed to insulate monetary policy from short-term political pressure.

The Chair’s responsibility is to the public, not the president.

Disputes over rates are common and historically consistent. They reflect the tension between political pressure and economic judgment. While the President appoints the Chair, monetary policy decisions are made by the Federal Open Market Committee, reinforcing the system’s independence.

To understand today’s environment, it is useful to look at historical President and Fed Chair relationships that illustrate the Chair’s recurring challenge of balancing political pressure with economic reality.

President Richard Nixon and Former Chair Arthur Burns

“I respect his independence,” President Richard Nixon said. “However, I hope that independently he will conclude that my views are the ones that should be followed.”

As Nixon prepared for re-election in 1972, he pushed Federal Reserve Chair Arthur Burns to keep rates low to support economic growth. Burns ultimately eased policy, resulting in short-term economic strength but contributing to the high inflation of the 1970s.

Behind the scenes, pressure from Nixon and his cabinet was persistent.

Nixon and his advisors made clear they believed tighter policy would risk both the economy and the election. Burns faced a difficult choice between institutional independence and political reality. Policy remained loose longer than it otherwise might have. Inflation began to build even as unemployment improved, setting up the stagflation that defined the decade. The episode is often cited as a clear case of political influence shaping monetary policy outcomes.

President Jimmy Carter and Former Chair G. William Miller

President Jimmy Carter appointed G. William Miller, who was widely seen as too cautious on inflation, laid-back, and dovish.

Miller served only 17 months before being replaced, amid oil price shocks, weak policy credibility, and broader economic instability. The episode reinforced the cost of a Fed perceived as too aligned with the White House.

Markets questioned whether the Fed would act forcefully enough to contain inflation, and Miller was reluctant to tighten aggressively, allowing inflation expectations to continue rising. The lack of decisive action eroded confidence in the central bank.

Carter ultimately moved Miller to the Treasury, replacing Richard Blumenthal, and replaced him as Chair with Paul Volcker during Carter’s “cabinet crisis”. This marked a clear shift toward restoring credibility and independence in monetary policy.

President Ronald Reagan and Former Chair Paul Volcker

President Ronald Reagan inherited Paul Volcker from Carter, who had already begun aggressively raising rates to fight inflation.

The policy triggered a deep recession but ultimately reduced inflation from a record high in 1980. Reagan publicly supported Volcker despite the political risk, demonstrating that central bank independence can involve short-term economic pain in pursuit of long-term stability.

The pattern is clear. Presidents want growth. The Fed is tasked with stability. The tension between the two is not a flaw. It is by design.

The Atlas View

At Atlas Analytics, our position is clear.

In an environment of accelerating growth and persistent inflation risk, interest rates should be higher, and policy should remain firmly insulated from political pressure.

Supporting Federal Reserve independence today is not about personalities. It is about preserving the institutional framework that made long-run American prosperity possible.

At Atlas Analytics, we use satellite-derived GDP nowcasting and proprietary AI models to help investors anticipate policy inflection points before markets price them in. If you want to trade this thesis or stress-test it against your own views, we welcome the conversation.

Let's Connect

This article was written with valuable research assistance from Morgan Reppert, Executive Operations Associate for Atlas Analytics.

The average hedge fund has returned ~5.3% per year over the last decade1.

A model portfolio informed by Atlas signals has returned nearly four times that amount in the first ten weeks of the year.

While the sample period is short, the early results illustrate the potential of the Atlas approach.

Atlas signals generated approximately 21% year-to-date in a model portfolio through a combination of systematic macro trades (such as shorting long-duration bonds and going long the USD) and arbitraging the deviations between fundamental value and market price for a bevy of ETFs.

In short: better economic measurement creates an informational edge in financial markets.

The performance reflects a repeatable framework that links forward-looking economic data with macro-exposed financial instruments.

Atlas converts satellite imagery into forward-looking economic indicators that inform both client research and, in this case, a demonstration portfolio used to illustrate how those signals can be applied in financial markets.

Atlas’ Portfolio Performance

Our recent performance is not a statistical gimmick. It is the recognition of a new way of viewing economic value through satellites.

As I’ve written about at length on our Substack, Atlas utilizes geospatial imagery and our proprietary, patent-pending algorithms (ROY and a forthcoming invention we’ll disclose shortly) to ingest pictures of Earth, transform this into economic data, and then use this to predict future GDP performance ahead of government releases.

With this forward-looking view on economic activity, we create price targets for a subset of macro-exposed ETFs and a coherent view of future likely macroeconomic conditions.

These signals can then be applied to financial markets through options or positions in the underlying securities.

The early results have been encouraging.

Atlas Portfolio Performance vs S&P 500

Since May 2024, the Atlas portfolio has produced cumulative returns of approximately 93%.

When compared to the S&P 500, the Atlas Portfolio has 22 percentage points of alpha in the first 10 weeks of 2026, 50 points of alpha over the last year, and 61 points over the last nearly two years.

On a transaction basis, nearly two-thirds have been winners.

Atlas Macro Strategy (One Year: March 2025 - 2026)

• Return: +72.9% annualized

• Volatility: 41.4%

• Sharpe Ratio: 1.69

• Alpha vs S&P: ~21%

A one-year Sharpe Ratio of 1.69, where 1.5 is generally considered strong and 2.0 is considered elite, compares favorably with many hedge fund strategies.

The early results suggest the framework is working.

The Atlas Trading Strategy

As I tell my financial clients, if you can predict GDP with both accuracy and timeliness, you can often anticipate the direction and magnitude of movements in financial markets.

I do this in two ways:

1. Arbitraging the Deviation Between Fundamental Value and Market Price for ETFs:

The market oscillates day-to-day for largely short-term sentiment and macro headlines that traders assign value to, often arbitrarily. I’ve long discussed the difference between fundamental value and market price for equities (for instance, see this article The Tale of Two Prices from the spring 2025).

Traders believe that a war in the Middle East, the assignment of tariffs during Liberation Day and other associated short-term events are selling opportunities. Although they might be, often the moves are much more exaggerated than they should be. Our Atlas signal cuts through this noise based upon 50 years of economic data to answer the basic question that financial analysts should be asking: Has the fundamental basis of economic activity as visible from the satellites changed due to the event?

If the answer is yes, then I update my priors and rebase our financial targets based on the data.

If the answer is no, then in fact this is a buying opportunity, as the move to the downside is overdone.

This is how you make money in the financial markets using statistics, rather than discretionary reaction.

2. Systematic Macro Trading Based on a Forward-Look at the Plausible Economic Environment

If you can predict GDP ahead of the market consensus, you have a vantage point to analyze the likely macro regime of the unfolding epoch. For instance, earlier this year I wrote that, despite calls from the consensus to the contrary, that interest rates from the Federal Reserve would be likely higher (not lower).

How did I come to this conclusion?

As I elucidated here in our article “Powell Paused. The Data May Force the Next Fed Move Higher”, two observations informed this view.

First, GDP was likely stronger than the market was pricing in. (As a side note, I was wrong for Q4 largely due to the Government Shutdown and Net Exports, as I’ve openly admitted. The BEA also revised Q4 growth down to 0.7% from 1.4% on March 13. That revision reinforces how volatile and backward-looking official GDP releases can be and why forward-looking indicators are useful for interpreting the evolving macro environment.)

Second, inflation would likely be more sticky than previously thought. Both CPI and PCE inflation have remained above the Federal Reserve’s 2% target.

As I wrote in Powell Paused: the combination of strong economic growth and sticky inflation is not an environment in which the Fed cuts. In fact, it is the opposite.

Recent minutes from the Federal Reserve’s FOMC show that several members are considering similar risks. And the bond market is waking up to the same reality, with this Bloomberg article suggesting bond yields are rising in anticipation of a higher benchmark interest rate.

Atlas data allowed me to identify and trade this opportunity early.

Two Illustrative Trades

How did I trade this in practice?

1. Arbitraging ETF Fundamental Value vs Sentiment Deviations: Short the XLI

As I stated above, if you can predict GDP, you can predict ETF prices. One example I’ve traded recently is shorting the XLI.

The XLI is the State Street sector spider for industrials. Despite pallid returns across the market this year (the NASDAQ is down 2% and the S&P is down 0.8%), the XLI has jumped nearly 12% at its peak on March 2.

This jump was spurred on bullish sentiment and some economic reality, but it was overbought and our Atlas data cut through that.

On February 22, I shorted it by buying puts (4 contracts, 171 strike price, March 27 expiration). The stock then summarily declined. I closed the contract on March 3 grossing approximately $1500.

As bullish sentiment has over-run its economic basis, I believed the XLI was over-valued and the position benefited when the broader market declined.

2. Systematic Macro: Short the TLT

I wrote three months ago that the consensus was wrong, that economic growth was too strong and inflation too high for persistent rate cuts, and therefore long-duration bonds were at risk of a violent repricing.

I traded this, buying long-dated puts on the TLT (25 contracts, 88 strike price, July 17 expiration).

Bonds rallied in the first two months of the year and I admit, I was nervous. But I stuck to my thesis. This last week, the TLT plummeted, dropping from 90.82 to 86.97 as of close on Thursday.

I closed 10 contracts on Thursday morning (recovering my initial investment); I will let the rest run using the house’s money to earn an asymmetric potential payoff.

The position benefited as Treasury yields rose following stronger economic data and hawkish Fed commentary.

What This Means for You

The Atlas framework is built on a simple premise: if you can measure economic activity earlier and more accurately than the market, you can trade ahead of consensus.

Satellite imagery provides a new dataset through which to observe the economy in near real-time. By converting those observations into macro forecasts and tradable signals, Atlas aims to create a systematic edge in financial markets.

The portfolio performance shown here simply illustrate how those signals can translate into financial market opportunities.

The results so far are encouraging. And as the dataset expands and the algorithms continue to evolve, the opportunity set may grow even larger.

Let's Connect

For the past several years, Atlas Analytics has been developing a simple idea:

If you can observe the real economy directly from space you can measure economic activity before the official statistics are released.

Our satellite-based models track patterns in construction activity, infrastructure usage, logistics networks, and other physical indicators of economic production. From these signals we estimate Core GDP, a measure of the domestic economy consisting of Consumption, Government Expenditures, and Fixed Investment.

The key insight is not only the numerical prediction of those indicators but the turning points. Our algorithms signal shifts in the trajectory of the real economy roughly one quarter before they appear in the official data.

This week we’re releasing an updated comparison between Atlas’ satellite-based estimate of Core GDP and the realized data from the Bureau of Economic Analysis.

The results show that signals captured from space track the underlying trajectory of the economy remarkably well—and may provide an early indication that growth is gradually slowing beneath the surface of the headline numbers.

Satellite Signals vs. Official Data

Since 2023, our satellite-based estimate of Core GDP has shown a strong relationship with the official data released by the BEA.

Across this period, the Atlas model demonstrates:

• Pearson correlation: 0.70

• Root Mean Squared Error (RMSE): ~0.77 percentage points (relative to the BEA’s third revision)

In other words, signals extracted from satellite imagery track the direction and magnitude of economic activity with surprising accuracy.

Even more importantly, the satellite signal typically leads the official data by roughly three months.

That lead time matters.

Government statistics arrive with delays and are often revised multiple times. By the time markets fully digest them, the underlying economy may already be moving in a different direction.

The goal of Atlas Analytics is to observe those movements as they happen.

The latest BEA print was temporarily reduced by the government shutdown at the end of 2025. Adjusting for that effect brings the underlying growth rate closer to ~2%, broadly consistent with the Atlas signal. Over the full sample since 2023, the satellite-based estimates maintain a correlation of 0.70 with official data and an RMSE of ~0.77 percentage points, indicating that the model continues to track the underlying direction of economic activity well.

The investment implication?

Markets react to changes in economic momentum rather than the level of GDP itself. Our satellite signals suggest that shifts in that momentum can be detected roughly one quarter before they appear in the official statistics.

The Trend Is Gradually Slowing

One feature of the data stands out clearly:

Core GDP appears to be trending gradually lower over the past several years.

The economy has not collapsed. Far from it.

But the underlying rate of growth has steadily moderated from the stronger pace seen earlier in the cycle.

Several forces may be contributing to this shift:

• The fading effects of post-pandemic fiscal stimulus
• Higher real rates weighing on investment
• Moderating consumer demand after several years of unusually strong spending

Individually, none of these forces necessarily signals an imminent downturn.

But together they suggest that the underlying pace of economic expansion may be cooling.

If the trend continues, it could eventually lead to a broader slowdown or recessionary environment. For now, the data suggests moderation rather than contraction.

Why Core GDP Matters

Headline GDP can often be misleading.

Two components—Net Exports and Private Inventories—can swing dramatically from quarter to quarter due to factors unrelated to the underlying health of the domestic economy.

To isolate the true momentum of economic activity, Atlas focuses on Core GDP, which captures the more stable components of economic growth: consumption, government spending, and long-term investment.

This measure tends to provide a clearer signal of underlying economic momentum.

However, accurately measuring Net Exports and Private Inventories remains one of the most difficult challenges in macroeconomic forecasting. Both components can create large surprises in GDP releases and often drive the gap between expectations and realized outcomes.

To address this challenge, Atlas is currently developing a new generation of algorithms designed to measure these components directly using satellite and geospatial data.

Early results are promising, and we believe these tools will meaningfully expand our ability to measure the full economy in near real time.

The Trading Advantage of Early Signals

The most powerful aspect of satellite-based macro measurement is timing.

Because Atlas’ Core GDP estimate tends to lead official data by roughly three months, it provides a window into economic momentum before it becomes visible in traditional statistics.

During volatile market periods, such as the turbulent weeks we have seen recently, having a clearer picture of underlying economic activity can be extremely valuable.

It allows investors to position ahead of the consensus narrative.

Using Atlas signals to guide our positioning, our trading strategy is currently up roughly ~6% year-to-date, while several major equity indices have struggled over the same period.

(We plan to share a more detailed performance breakdown in a future post.)

The goal is not simply forecasting.

It is turning economic insight into actionable investment decisions.

What Comes Next

Satellite-based measurement of economic activity is still in its early stages.

Over the past few months, Atlas has begun collaborating with several longstanding institutions in the macroeconomic and policy community to explore how satellite-derived economic indicators can complement traditional statistics.

At the same time, we are expanding our modeling framework to incorporate additional components of economic activity that have historically been difficult to measure in real time.

Together, these developments represent the next phase of Atlas’ work.

We look forward to sharing more about these efforts, and what they reveal about the economy, in the months ahead.

Stay tuned.

The Bottom Line

The satellites are telling a clear story.

The U.S. economy remains resilient but underlying growth appears to be gradually slowing.

And thanks to new sources of data, we can see these shifts months before they appear in official statistics.

That is the power of observing the economy from space.

Let's Connect

I had the pleasure of attending this year’s NABE Economic Policy Conference, “The Great Realignment: Navigating AI, Demographic, and Geoeconomic Change,” and left the meetings energized by both the intellectual honesty and forward-looking tone of the discussions.

The central thread running through the conference was clear: artificial intelligence is no longer a speculative tailwind but an active force reshaping economic performance in real time. Much of the dialogue focused, appropriately, on productivity, where gains may emerge, how quickly they may diffuse, and what it means for labor markets and capital allocation.

But an equally important theme, and one that resonated deeply with me, was measurement.

As AI accelerates the pace of economic activity, our traditional statistical frameworks, survey-based, lagged, and often revised months later, are increasingly strained in their ability to capture what is happening on the ground. Multiple panels touched on the need for new data architectures: higher-frequency, more granular, and alternative datasets capable of observing the economy as it evolves rather than after the fact.

As AI accelerates economic activity, the institutions and frameworks we rely on to measure it will have to evolve just as quickly.

One highlight of the conference was the discussion between Jeff Frieden (a valued contributor here on the Atlas Substack) and MIT’s Daron Acemoglu on the emerging political and economic order. Their conversation explored how technological transformation, industrial policy, and geopolitical fragmentation are interacting to reshape globalization’s next chapter. It was a thoughtful and nuanced dialogue that underscored how economics and political economy are becoming increasingly inseparable in the AI era. Still, the question remains: how will governments and individuals reconcile with the vast and frenetic change brought on by this most recent wave of innovation, and what will that mean for institutions going forward?

Another memorable moment was seeing Christine Lagarde recognized with the Paul Volcker Lifetime Achievement Award. It was a fitting tribute to her stewardship across international finance and central banking, and the standing ovation in the room reflected the depth of respect she commands across the global policy community. But it also felt emblematic of a deeper institutional transition underway. Central banking itself is being pulled into a new measurement regime, one where policymakers are increasingly expected to interpret higher-frequency signals, alternative datasets, and AI-derived indicators alongside traditional releases. The frameworks built for slower, lower-resolution economic data are now being stress-tested by a world that moves, and can be observed, in real time.

Stepping back, what struck me most was the degree of openness, across both public and private sector economists, to new tools and new methodologies. There is growing recognition that understanding the modern economy will require integrating machine learning, alternative data, and interdisciplinary approaches alongside traditional macro frameworks. If economic measurement becomes AI-enabled and more granular, the practical implications are significant: policy reaction times compress, informational advantage shifts toward those measuring activity first, and aggregate GDP becomes less sufficient as a standalone signal.

The future of economic measurement is being written now, and it will be faster, more granular, and increasingly AI-enabled. At Atlas, we are building for that world, not just to interpret the data, but to measure the economy as it unfolds.

This week, the BEA released its first estimate of Q4 2025 GDP at 1.4%, below our Atlas Analytics forecast of 5.2%.

We believe in addressing misses directly.

Forecasting quarterly GDP, particularly at the subcomponent level, is one of the most complex measurement challenges in macroeconomics. This release provides an opportunity to examine where divergence occurred and what it reveals about the structure of GDP itself.

Below is a decomposition of the variance.

Breaking Down the Gap

GDP is the sum of three major contribution buckets:

• Core GDP (Consumption + Government + Fixed Investment)

• Private Inventories

• Net Exports

Our variance relative to the BEA print was concentrated in two areas: Net Exports and Inventories, with an additional meaningful drag from Government spending that downwardly affected Core GDP.

1. Core GDP

Atlas forecasted 2.35pp versus the BEA’s 1.13pp.

The primary divergence within Core GDP came from Government spending, which subtracted approximately 0.9pp from growth following last fall’s government shutdown. That contraction meaningfully reduced headline growth and amplified the overall gap.

Importantly, private-sector activity signals (consumption + fixed investment) remained materially stronger than the headline figure suggests, and if Government spending had remained consistent with previous quarters instead of the protracted shutdown, the gap between Atlas’ Core GDP and the actual would have been negligible.

2. Private Inventories

Atlas projected 0.77pp versus the BEA’s 0.21pp.

While directionally consistent, inventories contributed less to growth than anticipated. Inventory accounting remains one of the most volatile components of quarterly GDP and is often revised in subsequent releases.

3. Net Exports

Atlas forecasted 2.05pp versus the BEA’s 0.08pp.

This was the largest source of variance.

Trade flows, particularly imports, can swing quarterly GDP materially due to timing effects, booking conventions, and seasonal adjustments. Measured trade activity and its contribution to GDP are not always perfectly synchronized in real time.

This quarter highlighted that volatility clearly.

Measurement Is Hard — Especially at the Margin

Quarterly GDP is constructed from thousands of data inputs, surveys, and accounting adjustments. Certain components, particularly Net Exports and Private Inventories, are inherently more volatile and prone to revision.

This release reinforces three realities:

1. Subcomponent forecasting is significantly more difficult than headline alone.

2. Trade and inventory dynamics can overwhelm otherwise stable private-sector growth.

3. Real-time measurement requires continuous refinement.

What We Are Doing

In response, we are:

• Operationalizing additional algorithms and model modules focused specifically on volatile trade and inventory dynamics.

• Continuing to refine our Core GDP tracking, where underlying private-sector signals remain consistent, while expanding our capacity to incorporate atypical government spending shocks and other non-recurring economic events.

• Conducting a full post-release decomposition and lag analysis.

Our objective is not short-term perfection.

It is a durable measurement improvement.

The Broader Signal

Despite the headline print, our Core GDP signal continues to indicate steady underlying economic activity.

Quarterly prints can be noisy.

Economic structure is not.

Understanding the difference between the two is precisely why high-frequency, observational data matters.

Transparency as Our Policy

We will continue to publish both our successes and our misses.

Forecasting is probabilistic. Measurement is iterative. Credibility comes from transparency.

More detailed analysis, including component-level diagnostics and model adjustments, will follow and we will be releasing updates to our key algorithms (including new ones) in the weeks to come.

As always, we appreciate your engagement and thoughtful dialogue.

Leave a comment

As 2025 came to a close, the dominant narrative was clear: the U.S. economy was running out of steam.

Slower consumption, tighter financial conditions, and trade imbalances led many economists to expect a soft finish to the year. Consensus forecasts drifted lower through the fall.

But our models were telling a different story.

While traditional forecasters leaned cautious, Atlas Analytics’ satellite-derived indicators across consumption, trade, and fixed investment remained firm. And now, the official data are beginning to reflect that strength.

Our final forecast for Q4 2025 U.S. GDP comes in at +5.2%, a strong acceleration into year-end.

Here’s how we got there:

The Indicators:

Core GDP
Real-time satellite measurements of industrial activity, energy demand, and consumer intensity pointed to sustained domestic resilience. Core growth contributed +2.6 percentage points, reflecting firm production and steady household demand.

Net Exports
Port-level imagery and shipping volume data showed improving trade flows late in the quarter. As export activity strengthened and the deficit narrowed, Net Exports added +2.1 percentage points to headline growth.

Private Inventories
After weighing on GDP earlier in the year, inventories flipped into a tailwind. Firms rebuilt stock amid solid demand, contributing +0.8 percentage points.

Add it up, and Q4 was not narrow or technical. It was a broad-based expansion across production, trade, and domestic demand.

Where Growth Is Happening

The strength was not confined to the national aggregates.

Our Q4 state-level forecasts show expansion dispersed across much of the country. The Southeast led with above-trend momentum across the Carolinas, Georgia, Tennessee, and the broader Gulf corridor, supported by manufacturing activity and logistics flows.

The Mountain West, including Arizona, Utah, and Colorado, continued to benefit from in-migration, construction, and business formation trends.

National GDP is a headline number and will reflect the sum of the state’s growth— but the signal appears first at the state level. When policymakers and investors focus only on the top-line number, they miss the geographic drivers and often respond after the window to act has closed

Atlas’ state-level GDP forecasts give those decision-makers something they’ve never had before: An independent, real-time read on the underlying economic drivers at the state level, before the official data confirms them.

Let's Connect

On Q1 2026

Early Q1 2026 nowcasts suggest moderation off a strong Q4 base. Consumption remains positive but is cooling. Trade contributions are stabilizing. Inventory accumulation is slowing after companies rebuilt stock levels at year-end.

The Federal Reserve held rates steady in January, and for now we expect policy to remain in a holding pattern. Broader macro-financial risks, including interest rates, fiscal pressures, and global capital flows, remain important swing factors. Looking further into late 2026, credible paths exist in both directions. Growth could firm if demand re-accelerates, or soften further if cooling deepens. Macro-financial risks (rates, fiscal pressures, global capital flows) remain important swing factors, but state-level activity data will provide the earliest signal of which path is emerging.

At Atlas, we remain fully data dependent. As new satellite, trade, and consumption signals come online, they will shape our views in real time and provide early signals of which path is emerging.

Don’t miss our Q4 2025 GDP Forecast video for a deeper dive and stay tuned for our 2026 Q1 Forecast.

Subscribe for Q1 2026 Updates

AI has rapidly become the centerpiece of economic debate, with claims ranging from an imminent productivity boom to warnings of mass displacement, extreme resource extraction to power data centers to the potential of a bubble event.

In this roundtable conversation, Atlas Analytics Founder and CEO, Jake Schneider sat down with Cliff Waldman and Daniel Bachman to discuss where AI is really taking the economy.

Cliff and Daniel bring decades of experience in economic forecasting, productivity, and industrial analysis, and offered thoughtful, data-driven perspectives that complement how Atlas thinks about macro trends and forecasting.

The economists spoke about the gap between AI hype and measurable impact, what past technology cycles can teach us, and what the data suggests about long-term growth. This is a grounded, evidence-based discussion about where AI may matter most over time.

Growth Outlook

The discussion opened with a reminder that most economics forecasters—including the Congressional Budget Office—have not meaningfully revised long-term productivity assumptions in response to generative AI. Trend labor productivity growth remains around 1.4%, roughly where it stood before AI became a mainstream topic.

The reason is historical: major technologies rarely show up cleanly or quickly in aggregate statistics. Electricity, railroads, computers, and the internet all took years before their productivity effects were visible in macro data. Short-term bursts of growth may reflect many forces at once, making attribution difficult.

From this perspective, AI may matter enormously in the long run, while changing very little about near-term growth forecasts today.

AI and the Victorian Railroad Mania

To better understand the future, the discussion weighed the significance of previous market episodes like the dot com bubble, internet boom, and even Britain’s 19th century railroad boom.

“When the British started building railroads, there was a huge financial boom. But in the end, British railroads actually had a lot of trouble in the 19th century being profitable.”

Railroads undeniably transformed commerce, logistics, and economic integration, yet many projects struggled for years to generate profits, despite massive investment and public enthusiasm. The episode illustrated a recurring pattern in economic history: technologies can deliver long-term societal value while disappointing investors in the short and medium term.

Applied to AI, the analogy cautioned that even transformative infrastructure can experience periods of overinvestment, volatility, and financial stress before finding a sustainable role in the economy without invalidating its underlying economic importance.

An Uneven Future, Revealed Only in Hindsight

Still, uncertainty dominates the outlook. AI is not a single technology but a constellation of tools whose effects will vary widely across firms, sectors, and regions. Its success depends not only on algorithms, but on management execution, labor integration, consumer strength, and demographic trends.

If AI accelerates entrepreneurship and enables new industries, it could reinforce long-term growth. If gains accrue narrowly or consumer demand weakens, today’s optimism may fade. As with every major technological shift, the decisive verdict will arrive slowly and only in hindsight.

More on Atlas Analytics forecasting and AI market insights here:

Click Here

Cliff Waldman, CEO, New World Economics, LLC., has been an active and in-demand public speaker on topics ranging from the U.S. and global economic outlooks to new markets, productivity, and automation. From 2003 to 2018, Cliff served as Senior Economist and Chief Economist of the Manufacturers Alliance for Productivity and Innovation (MAPI). He has spent nearly two decades writing and speaking on the global economic picture as well as a range of issues of central importance to the manufacturing sector, including productivity, demographics and emerging markets. His career has also included tenures as an economic researcher with a state government forecasting and policy research unit as well as with a small business research team in Washington, D.C. Cliff directed a large contract for the Small Business Administration on the entrepreneurship potential of the veteran and service-disabled veteran population. He has won three national research awards. He received his M.A. in economics from Rutgers University. Cliff can be reached at cliff@newworldecon.com.

Daniel Bachman, Ph.D., is an experienced U.S. and international macroeconomic forecaster and modeler. He is now retired, but from 2013-2024 he was the lead US Economic Forecaster for Deloitte. He also worked as a senior economic analyst and forecaster for the U.S. Commerce Department, Forecaster and model expert for Wharton Econometric Forecasting, and taught economics at Temple University. Mr. Bachman holds an M.A. and Ph.D. in Economics from Brown University and a B.A. in Political Economy from the Johns Hopkins University. Dr. Bachman maintains a blog that uses traditional methods to predict near term GDP, as well as providing opinions and books reviews on other economic topics. Daniel can be reached at danieldbachman@gmail.com and his blog, The Nowcast, can be found on Substack.

This article was written with valuable research assistance from Morgan Reppert, Executive Operations Associate for Atlas Analytics.

Two weeks ago, I introduced Atlas Analytics’ contrarian macro thesis.

As a reminder, I wrote:

Recall that up until that point, the consensus belief was: growth is slowing and the Fed will continue to cut.

On Wednesday, Jerome Powell, the Federal Reserve Chairman, paused – just as Atlas has been discussing with our clients.

Here’s where our view diverges even further from the consensus.

Instead of continuing to cut, as the market is pricing in throughout 2026, we see short-term rates going higher – not lower.

A Hawkish Pause?

Powell’s pause was broadly interpreted as benign. Markets barely reacted, and expectations for rate cuts remain firmly in place—if not at the March FOMC, then later this year.

But buried in the Q&A was a subtle shift.

In response to a question, Powell replies:

“The outlook for economic activity has improved… growth is on a solid footing,” and that while the risks to inflation and employment have diminished, they still exist — indicating that future rate moves will be driven by incoming data, not prior expectations.

Not prior expectation, but incoming data will drive future rate moves.

And Atlas Analytics knows that the incoming data will be strong.

The Interest Rate Corollary (Again)

As I wrote in my note Trump’s Challenge Leaves the Federal Reserve At A Crossroads two weeks ago: The corollary to strong incoming data is higher longer-term rates.

Not today, not next month, but – if the data comes in as strong as we expect – the conversation in the FOMC will shift by the summer, introducing the possibility of a rate hike in the fall of 2026 or the winter of 2027.

Atlas’ Preliminary Longer-Term Economic Forecast

So what is our satellite-powered GDP data showing – that the market and the FOMC doesn’t yet know.

Since Q1 2025’s slightly negative print, GDP growth has reaccelerated sharply.

Our satellite data points to approximately +5.0% growth in Q4 2025. While the official advance release was delayed by last fall’s government shutdown, the quarter is complete and the signal is already clear.

Looking ahead, we estimate Q1 2026 growth at roughly +4.5%, ahead of its expected late-April release.

If these estimates are even close, the implication is significant. U.S. growth is materially stronger than the market expects, and interest rates will need to move higher to contain inflationary pressure.

(We’ll be releasing our Q4 2025 video on our YouTube channel on Sunday, February 15th).

Atlas’ Preliminary Longer-Term Rate Forecast

What might the Federal Funds Rate look like if indeed growth is too strong and inflation too sticky?

The result: A policy rate surprise.

Using an applied Taylor Rule (a method that combines inflation and growth rates to arrive at the proper interest rate-level), and then augmenting it for a likely – but not guaranteed – hiking cycle, Atlas Analytics arrives at the chart below.

In plain terms: if growth and inflation evolve as our data suggests, today’s policy stance becomes accommodative—not restrictive—by late 2026.

If growth holds near +4–5% through mid-2026, the first serious discussion of hikes likely emerges in the second half of the year.

In our view, and without anchoring to precise timing, the implication of this chart is a Federal Funds Rate closer to 5.0% than 3.1%, the value proposed by the FOMC’s own Summary of Economic Projections.

What Does This Mean For You?

This is the type of insights made possible through Atlas Analytics’ satellite-based real-time GDP forecasts. We share these insights weekly with our clients so they can get ahead of the market.

While we are currently focused on the United States, Atlas’ mission is to bring satellite-based, real-time GDP insights to every country on Earth.

Whether you are an institutional investor, family office, government agency, or international organization, Atlas provides world-class macro data, financial targets, and economic insight. Reach out to learn more.

Contact Us

Bonus for Our Paid Subscribers: How to Trade This

If our thesis is correct—stronger-than-expected growth, stickier inflation, and a higher terminal policy rate—the implications for asset prices are asymmetric.

Below are three ways to position for a policy rate surprise.

Read more

Time-lapse satellite imagery of Las Vegas reveals the expansion of the built environment in near real time—new construction, site preparation, and infrastructure growth visible months before appearing in official economic statistics from 2015 to 2026.

Fabulous Las Vegas – the city of gambling, goofing off, and perhaps, gauging economic activity.

Previously in A Picture Is Worth A 1000 Words, Part I and Part II, we explored both our key algorithm ROY (named after our founder’s grandfather), and our discovery of a Geospectral Signature that uniquely identifies each space and place by its reflective resonant imaging measurable from outer space.

Today, we return to ROY to explore what it is that Atlas Analytics’ is looking at in our proprietary satellite-based algorithms: the expansion of the built environment.

To this end, the GIF above is illustrative – using time-elapsed satellite imagery, we can literally see new buildings (including Vegas’ newest and grandest structure, The Sphere – notice the top right of our image) being erected in near real-time.

Why Construction?

We’re interested in construction—so let’s make this concrete.

We don’t need to measure the number of cars in Walmart parking lots when we can see that Walmart is building stores–the demand and growth is there. That construction represents real dollars being paid to the local populace in wages, and real dollars that are (partly) spent in the local economy.

Extrapolate this to other sectors of the economy. Increases in the service sector can be seen by construction of hospitals, hotels, and restaurants. Upzoning developed areas for increased housing density allows population growth, increasing a county’s tax base and labor pool.

The blue line shows headline U.S. GDP growth as reported by the federal government, while the red line reflects reported new housing units from the St. Louis Fed (FRED).

The chart above illustrates the relationship between a key component of the construction economy—new privately owned housing starts—and overall U.S. GDP growth over the past 25 years.

How Do We Measure This Change?

There’s an old aphorism: “Cranes in the air, buyer beware.”

But what if you could measure the growth of an area – before the cranes appeared.

The construction of a building has substantial economic impact. Heavy equipment must be transported to the site, land prepared, and foundations poured. Framing follows, then roofs, windows, and doors, before interior build-out, landscaping, parking, and road improvements complete the process.

Each of these steps leaves a distinct multispectral footprint—changes in surface reflectance, material composition, shadow geometry, and activity density—that we observe continuously through satellite imagery.

Because these signals emerge before construction is completed—and often before it is officially reported—they allow us to detect inflection points in local and national economic growth well ahead of traditional statistics.

What It Means for You?

Atlas Analytics measures real economic activity before it appears in official statistics. By observing construction and physical expansion directly from space, we generate signals ahead of government data releases—often weeks or months earlier.

That timing matters. Markets move on expectations, not confirmations. Early visibility into economic inflection points provides meaningful informational advantage to investors, policymakers, and institutions.

We use these signals internally as well. Between November 1, 2024 and November 1, 2025, Atlas strategies informed by this data generated a 54% return.

We publish these insights weekly—translating satellite-derived signals into actionable macro views for investors and institutions. Contact us to learn more.

Last Sunday, Federal Reserve Chair Jerome Powell did something rarely seen from a sitting central banker: he publicly drew a line.

In a public statement responding to growing political pressure tied to “construction costs” and broader policy grievances, Powell made his position unmistakable:

This isn’t about renovations or testimony. It’s about whether monetary policy will be set by economic evidence — or by political intimidation.

That distinction matters more than most market participants currently realize.

Beneath the headlines lies a much larger story — one with direct consequences for interest rates, inflation, and U.S. economic growth in 2026 and beyond.

Powell’s stance matters because the economic backdrop he is responding to is very different from what markets currently assume.

The Consensus View — and Why It’s Wrong

The prevailing market thesis is simple:

• Growth slows

• Inflation fades

• Rates fall through 2026

At Atlas Analytics, we believe the opposite is increasingly likely.

Not because of ideology — but because the data no longer support the consensus narrative.

The Atlas Macro Thesis: Growth Is Accelerating

Here is what the economy is telling us:

• Q2 2025 GDP: 3.8% (BEA final)

• Q3 2025 GDP: 4.3% (BEA first estimate)

• Q4 2025 GDP: ~5.0% (Atlas preliminary estimate)

And our proprietary satellite-based GDP model, ROY, suggests that Q1 2026 growth will remain comparably strong.

This is not a decelerating economy.
It is an economy running well above trend.

The independent real-time nowcasts from the Atlanta Fed’s GDPNow for Q4 (5.3% as of January 14) corroborates Atlas’ economic picture. Yet markets continue to price a slowdown that has yet to materialize.

More on Atlas Insights Here

Inflation Isn’t Gone — It’s Sticky

December CPI tells the second half of the story.

At 2.7% year-over-year, inflation is not surging — but it is clearly above the Fed’s 2% target, and far from conclusively defeated.

With growth accelerating and demand remaining firm, inflation risks are asymmetric to the upside.

This places the Federal Reserve squarely back at the fulcrum of its dual mandate:

• Full employment remains resilient.

• Price stability is increasingly fragile.

In that configuration, the policy implication is not easing.
It is restraint.

The Interest Rate Corollary

Let’s follow the logic to its conclusion.

If:

• GDP sustains growth near 4–5%, and

• Inflation remains above target,

Then the Federal Open Market Committee will face a stark choice:
Defend price stability — or risk a renewed inflation cycle.

History is clear on this point.

In such an environment, the appropriate policy response is not rate cuts.

It is higher real rates.

That means the next major move in U.S. monetary policy is more likely to be tightening, not easing — potentially as early as the second half of 2026.

A Historical Parallel: The Mid-1990s

The closest modern analogue may be the mid-1990s under Chairman Alan Greenspan (my first boss), when the Fed engineered one of the few genuine soft landings in U.S. history.

During that period:

• Growth remained strong

• Inflation risks were contained only through disciplined policy

• The average effective federal funds rate was 5.3%

Today, the effective rate sits near 3.6% — materially below that historical benchmark, despite an economy that may be running just as hot.

Somewhere between those two numbers lies a more realistic equilibrium.

The lesson from the mid-1990s is that strong growth required higher policy rates than today’s to sustain a soft landing.

Why Politics Now Matters More Than Ever

This brings us back to the emerging tension between the White House and the Federal Reserve.

For more than a century, central bank independence has been a cornerstone of U.S. economic credibility, anchoring inflation expectations, stabilizing markets, and insulating monetary policy from short-term political incentives.

That independence is now being openly tested.

The outcome will not merely shape the next election cycle.
It will shape the trajectory of U.S. growth, inflation, and financial stability for decades.

The Atlas View

At Atlas Analytics, our position is clear.

Not politically — but economically.

In an environment of accelerating growth and persistent inflation risk, interest rates should be higher — and policy should remain firmly insulated from political pressure.

Supporting Federal Reserve independence today is not about personalities.
It is about preserving the institutional framework that made long-run American prosperity possible.

Call to Action

This is not just a macro opinion — it’s a positioning framework.

At Atlas Analytics, we use satellite-derived GDP nowcasting and proprietary AI models to help investors anticipate policy inflection points before markets price them in.

If you want to trade this thesis — or stress-test it against your own — we’d welcome the conversation.

Get in Touch

In A Picture Is Worth 1,000 Words, Part II, Atlas Analytics introduced our ability to forecast not only headline U.S. GDP, but also economic activity for all 50 states plus D.C.

As many political pundits have proffered: “So goes the economy, so goes the election.”

Well, in our case, so go the states’ GDP, so goes the entire economy.

Using our GDP forecast for every U.S. state, Atlas is able to ascertain not only what overall GDP growth will be – but which underlying geographies are driving it.

With 2025 now in the proverbial books, we will soon release our Q4 GDP forecast on YouTube and here on our Substack, but before we do, we wanted to give a small preview of what to expect.

Strap in for another big quarter.

With Core GDP (our central statistic that we monitor through satellite imagery), Private Inventories and Net Exports all trending very positively, we’re expecting another huge quarterly GDP print.

(For those not following the headlines, the BEA’s initial Q3 GDP estimate came in at 4.3%. As with all first estimates, revisions are expected, and we’ll do a full comparison with Atlas’ forecast once the final data is released later this month, currently scheduled for January 22).

With several new clients utilizing our state-level forecasts for their state’s official macroeconomic and budget forecasting, we now answer the question: Why State-Level GDP matters?

So Goes the States, So Goes the Economy…

National GDP is a headline number — but it is not a monolith.

Every quarter, U.S. economic growth is built from 50 distinct state economies that often move at very different speeds and for very different reasons. Energy booms in Texas, logistics surges in Georgia, tech slowdowns in California, housing cycles in Florida — these forces don’t cancel out neatly. They compound.

That’s why Atlas doesn’t just ask “How fast is the U.S. growing?”
We ask: Where is growth actually coming from — and where is it fading?

Our Q4 2025 state-level forecast shows exactly this divergence:

• Strong momentum across much of the Southeast and Mid-Atlantic,

• Continued resilience in parts of the Mountain West,

• Mixed signals in the industrial Midwest,

• And selective softness in pockets of the Upper Plains and coastal Florida.

National GDP will reflect the sum of these movements — but the signal appears first at the state level.

When policymakers, investors, and business leaders focus only on the top-line number, they miss the geographic engine underneath it and often react after the window to act has closed.

The Hidden Link: Growth Today, Borrowing Costs Tomorrow

State GDP doesn’t just describe economic health — it quietly prices capital.

In the second chart above, we show something that surprises many first-time viewers:
Across two decades of data, states with stronger GDP growth tend to face lower borrowing costs over time.

The relationship isn’t perfect — markets never are — but the direction is consistent:

Economic momentum becomes fiscal credibility.
Fiscal credibility becomes cheaper capital.
Cheaper capital becomes a long-term growth advantage.

This matters because:

• States issuing bonds to fund infrastructure, schools, and transit

• Cities planning multi-year capital programs

• Agencies managing pension and budget forecasts

…are all making decisions today based on assumptions about tomorrow’s growth.

Atlas’ state-level GDP forecasts give those decision-makers something they’ve never had before:

An independent, real-time read on economic trajectory before official data confirms it.

More on Atlas

Why Our State Agency Clients Care

Our state partners don’t come to Atlas because they want prettier charts.

They come because timing is everything.

Official state GDP data is released with long lags and heavy revisions. By the time traditional indicators confirm a slowdown or an acceleration, budget assumptions, issuance plans, and capital allocations are already set.

Atlas changes that dynamic.

Using satellite-derived signals — from construction starts to port throughput to industrial activity — we give agencies:

• Earlier warnings of inflection points

• More confident budget baselines

• Independent validation of internal forecasts

• Stronger narratives for legislatures, bond markets, and rating agencies

In practical terms, that means:

• A state treasury adjusting issuance plans before spreads widen

• A budget office stress-testing revenue assumptions before tax receipts fall

• An economic development agency targeting regions that are actually accelerating, not just visibly active

This is what modern macro looks like — not reactive, but anticipatory.

The Bigger Picture

When we say, “So goes the states, so goes the economy,” we mean something very literal.

America’s next business cycle won’t arrive evenly.
It will emerge state by state — through labor markets, ports, factories, housing starts, and energy corridors.

Atlas’ sub-national GDP framework is built for that reality.

Not just to predict the next number.
But to see momentum forming before the rest of the world does.

Work With Us

If you’re:

• A state or local agency responsible for budgeting, forecasting, or capital planning

• An investor allocating across regions and sectors

• A research institution studying the geographic drivers of growth

• Or simply someone who believes that macro deserves better tools

We’d love to talk.

📩 Reach us at below on our Substack
📊 Explore more at www.atlasanalytics.com
🎥 Watch our upcoming Q4 GDP forecast on YouTube later this month

Because the future of economic insight isn’t just national.
It’s state by state — from space.

Let's Connect

If a picture is worth a thousand words, then satellite imagery may be worth an entire economic theory.

In “A Picture Is Worth a Thousand Words, Part II,” Atlas Analytics introduced a novel finding: every place has a unique Geospectral Signature.

As we wrote:

Our working hypothesis is that each geography blends its built environment, land use, and vegetative patterns differently, producing distinct spectral signatures that map onto local economic structures.

Today, in collaboration with Columbia University Professor and noted author, Jeffry Frieden, we explore the broader implications of this insight across two foundational domains: economic development and political economy.

Specifically, we ask how economic geography—long understood qualitatively—can now be observed, measured, and modeled quantitatively:

• Why do some communities grow rapidly while others stagnate or decline? To what extent are these outcomes shaped by physical, infrastructural, and vegetative endowments?

• Which policies foster durable growth—and which impede it? Can satellite-derived geospectral signatures help predict where specific policies are likely to be effective?

• How do different communities express their unique geospectral signatures, and can these patterns help explain persistent political divides—such as rural conservatism and urban liberalism?

• Does the concept of a geospectral signature offer a plausible framework for understanding the rise of populism in the United States and the secular decline in global trade integration?

We do not claim to have definitive answers to these questions. Instead, we aim to open a new aperture for economic inquiry—one that allows political economy and development to be studied through a spatial, empirical, and satellite-based lens—and to propose promising avenues for future research.

More on Atlas Analytics

Economic Geography Meets Economic Development

From venerable institutions like the World Bank and IMF to research networks such as J-PAL and local development practitioners, one central question has long animated the field of economic development: what actually moves the needle for place-based growth?

The uncomfortable—but widely acknowledged—answer is that there is no settled consensus.

A rich array of theories exists, yet academic “best practices” often reflect what is empirically fashionable rather than what proves robust across time and place. Dig deeper, and the contradictions become clear. Many policy prescriptions directly conflict with one another. The Washington Consensus of the late twentieth century emphasized trade liberalization and minimal state intervention—just as earlier East Asian success stories such as South Korea and Taiwan pursued protectionist, state-led industrial strategies to foster domestic manufacturing. China’s subsequent rise followed a similarly heterodox path, blending global openness with extensive industrial policy.

The result is a development canon rich in insight, but fragmented in guidance.

So what, if anything, can satellite imagery add?

We do not yet claim to have the answer. But we believe we have a credible way to arrive at one.

Using satellite data spanning more than fifty years, Atlas Analytics has identified persistent spatial patterns that both explain historical growth trajectories and enable real-time GDP nowcasting. These patterns reflect how each geography uniquely combines its built environment, land use, infrastructure, and vegetation—what we call its geospectral signature.

This raises a natural question: what if, instead of using satellite imagery solely to predict future growth, we used it to infer which policies worked in the past—and where?

A region’s economic growth depends powerfully on its endowments: the physical characteristics of the land and its resources, along with what humans have created upon those characteristics. This helps explain what our research suggests: regions with similar geospectral signatures often exhibit similar growth dynamics. Geographic units with comparable physical and ecological characteristics often share similar economic and even policy outcomes. Policies that contribute to sustained growth in Benin may be more likely of success in Lesotho—a country we hypothesize has a similar geospectral signature. Conversely, policies that fail to generate physical and economic expansion in one region should be treated with caution when applied to geospatially analogous contexts.

To be sure, endowments are not everything. But they affect powerfully the interests of the people that inhabit a space, and the economic and political institutions those people create.

This approach does not promise a universal development blueprint. But it does offer a systematic, empirical framework for narrowing the policy space—grounded not in ideology or fashion, but in observed physical and economic reality.

This is the direction Jeff and I believe economic development research should move—and it forms the conceptual foundation for Atlas Analytics’ own consulting and advisory work.

The Political Economy of Place

Geospectral signatures may also help explain why politics and policies diverge sharply across space. Political economy, at its core, is concerned with how material interests shape political behavior. A central insight of Jeff’s work on trade and globalization is that political cleavages are not ideological accidents, but the outcome of uneven economic developments—developments that are deeply place-based1. Individuals and communities form political preferences through their lived economic experience, which depends fundamentally on the local environment. The local resource base, the local infrastructure, the local industrial structure – these have a profound impact on the risks they face, and the degree to which they benefit—or suffer—from economic integration.

Geospectral signatures provide a way to observe these local environments directly. Satellite imagery captures the physical imprint of economic structure: dense urban agglomerations anchored in services and knowledge industries; logistics corridors tied to global trade; land-intensive rural regions reliant on agriculture, raw material extraction, or legacy manufacturing. These spatial configurations map the distributional logic emphasized in Jeff’s analysis of trade politics. Regions characterized by diversified, globally connected economic networks tend to favor openness, state capacity, and redistribution. By contrast, regions characterized by concentrated, immobile, or declining economic activities often prefer protection, are skeptical of centralized institutions, and resist further integration. The familiar urban–rural political divide, in this view, is not merely cultural—it is spatially and materially grounded.

This perspective helps clarify the political backlash against globalization. It is well known that the turn toward populism is highly geographically concentrated in declining industrial areas: the North of England, northern France, eastern Germany, the American Industrial Belt. Jeff has argued that populism’s appeal in these areas is the result both of industrial decline – due to globalization and technological change – and of the failure of political and economic institutions to manage adjustment costs2. Geospectral signatures allow us to sharpen that claim. Regions with rigid physical infrastructures and limited capacity to adapt—what we might call geospectral lock-in—are more vulnerable to trade shocks and technological change, and thus more likely to experience political backlash when adjustment fails. By contrast, regions whose geospectral signatures evolve over time—through new infrastructure, land use transformation, or industrial diversification—appear better able to absorb shocks without destabilizing political consequences.

Critically, this framework does not imply political determinism. Institutions, politics, parties, and policies still matter enormously. But geospectral analysis makes the economic foundations of political conflict visible in physical space, offering a powerful complement to traditional political economy. Moreover, it points toward a constructive path forward. The same satellite-based insights used to understand why development succeeds or fails can inform how societies might reduce political polarization: by targeting investment, infrastructure, and industrial policy to help lagging regions adapt rather than stagnate. Economic development and political economy are two components of the same spatial reality—and satellites may help us see how to address it.

In Lieu of A Conclusion

This article does not end with a conventional conclusion, but with an invitation. Our aim has not been to offer a new grand theory of growth or politics, nor to claim that satellite imagery alone can resolve longstanding debates in economic development and political economy. Rather, we have sought to open a new aperture—one that allows the physical organization of place to be observed, measured, and analyzed alongside institutions, policies, and preferences.

By making economic geography visible at scale and over time, geospectral signatures offer a way to ground theories of development and political behavior in empirical reality. They provide a common language through which scholars, policymakers, and practitioners can better understand why similar policies produce divergent outcomes across space, why economic shocks generate political backlash in some regions but not others, and why adaptation succeeds in some places while stagnation persists in others.

The promise of this approach lies not in determinism, but in diagnosis. If we can see how economies and communities are structured in physical space—and how those structures evolve—we can design policies that are better matched to local conditions, more resilient to shocks, and more attentive to the political consequences of economic change. In this sense, economic development and political economy are inseparable: both are fundamentally about place.

If a picture is worth a thousand words, then satellite imagery may help us see—more clearly than before—how place, politics, and prosperity are bound together, and how they might yet be realigned.

Leave a comment

Jeffry Frieden is Professor of International and Public Affairs and Political Science at Columbia University, and Professor of Government emeritus at Harvard University. He specializes in the politics of international economic relations. Frieden is the author of Global Capitalism: Its Fall and Rise in the Twentieth Century and its Stumbles in the Twenty First (2006, second edition 2020); Currency Politics: The Political Economy of Exchange Rate Policy (2016); and (with Menzie Chinn) of Lost Decades: The Making of America’s Debt Crisis and the Long Recovery (2011). Frieden is also the author of Banking on the World: The Politics of American International Finance (1987), of Debt, Development, and Democracy: Modern Political Economy and Latin America, 1965‑1985 (1991), and is the co-author or co-editor of over a dozen other books on related topics. His articles on the politics of international economic issues have appeared in a wide variety of scholarly and general-interest publications.

View Jeffry Frieden’s website and list of publications here.

TLDR: Atlas Analytics expanded our team, launched multiple pilot programs with institutional investors and family offices, delivered its strongest forecasting performance yet, and continued to prove that satellite-based, real-time macro forecasting is not just possible — but investable.

Ad Astra per Aspera — “to the stars through difficulty” — is a phrase born from exploration. Literally, it means rising upward through turbulence; contextually, it speaks to the work of pushing past old limits to see the world more clearly.

This captures the spirit of Atlas Analytics. By expanding the aperture of economic inquiry — looking not just at surveys or lagged releases, but at the Earth itself — we are proving that the path to better macro measurement runs through new perspectives. Satellite imagery, artificial intelligence, and machine learning give us a higher vantage point from which to understand the economy in real time. The journey is not without its challenges, but the destination is a clearer, faster, and more accurate understanding of economic activity.

And in 2025, that journey took a major leap forward.

With 2026 drawing near, Atlas is stepping into the new year with more momentum, clarity, and proof points. What began as a bold experiment in satellite-based macro forecasting in my early days working under the tutelage of Alan Greenspan has evolved into a validated, forecasting engine powering investment decisions, institutional pilots, and a growing team.

As this year comes to an end, we take a look back at Atlas’ key predictions, milestones, and what we have in store for 2026.

As Frank Sinatra said, the best is yet to come!

What We Achieved in 2025:

1. Atlas Leads, Government Data Confirms: Our Weekly Predictions Precede BEA Revisions with Accuracy and Alacrity

Atlas Analytics’ track record consistently shows a very strong correlation between our forecasts and the BEA final estimates.

Our year-in-review analysis reflects results through Q2 2025; Q3 will be discussed separately once revisions and component diagnostics are complete.

Despite the variability of the BEA releases and the longest U.S. government shutdown yet, ROY remained steady. ROY’s track record consistently shows an extremely strong correlation between our estimates and the BEA’s final estimates, released nearly three months later.

After the release of the BEA’s 2025 NIPA Annual Update, Atlas’ historical error rate tightened to 0.5 percentage points. Reaffirming that our independent, real-time signals anticipate the final picture long before it becomes “official”.

2. ROY Generated a 54% Annualized Return

Our macro-signal portfolio returned 54% over the past 12 months. That performance didn’t come from stock-picking. It came from reading the underlying economy in real time before the numbers were published, revised, and re-revised.

3. State-Level Forecasting Became a Core Atlas Product

We can now use ROY to evaluate predictive strength across all states for the past 15 quarters, showing where the model performs best and what these patterns reveal about the structure of the U.S. economy, including for Q3 2025 below:

This year we expanded beyond national GDP to produce state-by-state:

• Forecasts and trend analysis

• Correlation and cluster maps

• RMSE accuracy scoring

These tools became increasingly essential for regional investors, supply-chain teams, and public-sector analysts navigating uneven economic conditions.

4. Pilots With Institutional Investors & Family Offices

In 2025, Atlas launched multiple pilot programs with institutional clients and family offices — many now integrating ROY directly into investment committee workflows.

Interested? Let's Connect

5. Expanded Team → Expanded Capacity → Go to Market

Atlas grew from a solo project to a five-person team (including two advisors), increasing our ability to build, model, publish, and support client requests at a much faster cadence. We anticipate more than doubling our client capacity in the new year.

Looking Ahead to 2026

With data uncertainty likely to persist — from delayed releases to increasingly volatile revisions — the need for reliable, real-time forecasting has never been clearer.

Atlas enters 2026 with:

• A validated forecasting engine

• Strong financial performance

• Active institutional and retail pilots

• Expanding models across national, state, and sector levels

• A growing team

Our mission is simple: Bring clarity to an economic system that increasingly lacks it.

We invite you to join us as we leverage our improved forecasting accuracy, expanding partnerships, and innovative solutions to meet evolving client needs. Whether you’re looking for data-driven insights or seeking a strategic partnership, we welcome the opportunity to collaborate with you.

Thank you for your readership and following along with us. Here’s to a very happy, healthy, and more data-stable 2026!

Till next year!

Ad astra per aspera,

Jake Schneider, Founder & CEO of Atlas Analytics

This article was written with valuable research assistance from Morgan Reppert, Executive Operations Associate for Atlas Analytics.

July 1944 (1806802; Credit: U.S. Office of War Information in the National Archives)

GDP, again?

Who cares about Gross Domestic Product — some arcane old statistic from a bygone era?

You do.

GDP is the single number that policymakers, investors, CEOs, teachers, farmers, diplomats, and families rely on to understand whether life is getting better or worse. When GDP rises, your standard of living generally rises with it: more income, more investment, more jobs, and more freedom to enjoy the parts of life that happen outside of work.

You’ve heard me talk about Atlas Analytics’ real-time GDP forecasting — how we anticipate economic turning points weeks or months before government agencies publish their numbers. But beneath all of that sits a fundamental question:

What actually is GDP? Where did it come from? And why does it still matter in 2025?

Let’s take the journey — from 17th-century war planning to the satellite-driven economy of today.

What Is GDP, What Does It Measure, and Why Does It Matter?

GDP is the market value of all final goods and services produced within a country over a given period. It remains the world’s most widely used benchmark for economic size, growth, and performance. Governments use it to calibrate fiscal policy; central banks use it to set interest rates; firms use it to guide investment; investors use it to decide where capital should flow.

And yet, GDP is a blunt instrument — powerful in what it can describe, but limited in what it can see. That tension is exactly why Atlas exists.

To understand how we got here, we need to go back — way back.

GDP: A (Brief, Surprisingly Dramatic) History

Source: Eurostat, OECD, and World Bank (2025); Bolt and van Zanden Maddison Project Database 2023; Maddison Database 2010.

The story of GDP is not the story of an economic formula. It’s the story of war, industrialization, crisis, and global reinvention.

The Proto-GDP Era: Counting Nations for War (1665–1870s)

• 1665 — British scientist William Petty produces the first national accounts for England and Wales to estimate the resources available for the Second Anglo-Dutch War.

• 1781 — At the request of Louis XVI, France produces a sweeping financial assessment — in part to justify more borrowing (which, in hindsight, didn’t work out).

• 1870s — The Industrial Revolution spreads across Europe, and governments begin building systematic economic accounts.

The early purpose was clear: to know whether a country could finance a war or survive one.

The Birth of Modern GDP (1930s–1940s)

• 1934 — Amid the Great Depression, economist Simon Kuznets delivers the first U.S. national income report to Congress, showing a devastating 50% collapse in output since 1929.

• 1944 — Weeks after D-Day, 44 nations meet at Bretton Woods, establishing GDP as the universal yardstick for rebuilding the postwar world.

GDP became the backbone of global economic planning because everyone needed one statistic they could trust.

The Golden Age and Growing Doubts (1945–1990s)

• 1945–1973 — Explosive industrial growth, suburbanization, globalization. GDP captures it all: the “Golden Age” of economic expansion.

• 1986 — After years of stagflation and social upheaval, economists begin criticizing GDP’s blind spots: welfare, inequality, environmental degradation.

• 1993 — China becomes the last major economy to formally adopt GDP reporting — solidifying GDP’s position as the global standard.

The Crises that Exposed GDP’s Limits (2000–2024)

• 2008 — The financial crisis erupts, and GDP misses nearly all early signs of systemic fragility.

• 2010 — Ghana revises its national accounts, increasing GDP by 60% overnight — revealing how fragile and inconsistent measurement can be.

• 2020 — COVID shutters the global economy down; satellite indicators outperform traditional models.

• 2022 — Russia invades Ukraine; satellite data again becomes essential for estimating damage, supply disruptions, and agricultural loss.

• 2024 — Atlas Analytics incorporates, building the next generation of real-time economic measurement for the digital and geospatial era.

The world learned something crucial: GDP is indispensable — but, on its own, insufficient.

Leave a comment

Why Atlas Matters

GDP remains the world’s economic anchor — but its limitations have become impossible to ignore.

We are entering an era of:

• Faster business cycles

• Larger, more frequent shocks

• Governments taking longer to produce data

• Digital sectors outgrowing the frameworks designed to measure them

• Investors needing real-time macro signals rather than backward-looking estimates

Atlas addresses this by building the first independent, continuously refreshed, satellite-driven, algorithmic view of the economy — an infrastructure capable of measuring growth not in quarters, but in days.

If the past few turbulent years have taught us anything, it’s this:

We cannot rely solely on government statistics to understand a global economy that moves at digital speed.

That is why Atlas exists — and why GDP’s origin story is not just history.
It’s the beginning of the next chapter.

GDP changed the world once. Real-time measurement will change it again.

If you’re following Atlas, you’re already ahead of the curve.
Help others get there too.

• Subscribe for weekly “satellite macro” insights

• Explore our research at atlasanalytics.com/insights

• Reach out to access Atlas’ real-time GDP & trade indicators

The next generation of macroeconomics is being built right now — and you’re part of it.

Refer a friend

This article was written with valuable research assistance from Morgan Reppert, Executive Operations Associate for Atlas Analytics.

Last week I sat down with Barry Moline on The Great Ideas Podcast to discuss something that, on the surface, sounds like science fiction: predicting GDP using satellite imagery.

To my pleasant surprise, the conversation pushed into exactly the themes I think matter most—how the world measures economic activity, why our current tools are structurally broken, and what happens when forecasting leaves the basement and enters orbit.

Below is a distilled version of the conversation and its implications for markets, businesses, and anyone making decisions in a volatile macro environment.

1. The Core Question: What If We Could Literally See the Economy Instead of Merely Inferring It?

Traditional macroeconomic forecasting is slow, noisy, and heavily anecdotal. GDP arrives with a three-month lag. Inflation numbers bounce with revisions. The Federal Reserve still uses the Beige Book—essentially a nationwide “how are things going?” phone tree.

Meanwhile, satellites orbit Earth every 90 minutes, revisiting the same coordinates every ~5 days, capturing unbiased physical evidence of economic expansion.

The founding insight behind Atlas Analytics is simple:

A picture is worth a thousand regressions.

During my time at Harvard and Oxford—studying economics by day and remote sensing/computer vision by night—I built a patent-pending algorithm, ROY (Remote Orbital Yield), that extracts the expansion of the built environment from satellite imagery.

Highways, factories, rooftops, logistics hubs, commercial floorspace, ports—the literal physical footprint of economic activity.

And it turns out we see something quite powerful:

The expansion of the built environment is one of the best leading indicators of GDP growth we’ve ever measured.

2. Why ROY Works: Seven of the Top Ten Predictors Are From Space

One of Barry’s questions that stood out in particular was: “How does AI weigh satellite data versus traditional indicators?”

Here’s the short answer:

Seven of the top ten variables in ROY’s machine-learning model come from satellite imagery—not lagged GDP, not CPI, not housing starts.

That’s a staggering result for the field of macroeconomics, and it explains why ROY consistently outperforms the Federal Reserve and major Wall Street consensus forecasts.

The underlying reason is structural: economic activity happens in areas of agglomeration—dense clusters where 90% of the world’s economic output takes place on just 16% of its land1. Satellite imagery sees those expansions the moment they occur.

Governments, by contrast, wait three months… then revise… then revise again.

3. Why Weekly Data Changes the Game

As mentioned in the episode, the U.S. government uses a highly manual, antiquated process to produce GDP four times a year. The data is pulled from a myriad of sources: surveys, census data, panels, sector reports, state records, conference calls, and more. The process is incredibly labor intensive, and the estimates are produced with significant, inconsistent lag, and several revisions.

Atlas provides our clients with 50+ points on a weekly basis.

By running ROY weekly, we convert a lumpy, outdated quarterly metric into a dynamic signal that reveals:

• Micro-movements of the business cycle

• Inflection points before they appear in official data

• Early warnings of recessions

• Evidence of overheating or overvaluation in specific macro-exposed financial indices

While government statistics arrive with long lags and revisions, Atlas models detect economic turning points as they happen.

4. Yes, Market Timing Is Now Possible (Sorry Warren Buffett)

One of the bigger reactions during the interview came when I said something that would get me thrown out of some economics departments:

Market timing is no longer impossible. It is now quantifiable.

Using ROY signals, Atlas Capital—my own portfolio where I trade exclusively on Atlas data—has returned roughly 60% year-to-date (~54% to be exact).

We don’t pick individual stocks. We avoid idiosyncratic, equity-specific risk. Instead, we trade macro-exposed ETFs whose performance is tightly linked to national economic cycles.

If ROY says tech (XLK) is fundamentally overpriced relative to GDP conditions, we act accordingly.

If ROY says we’re entering a pullback, we reposition before the market catches up.

It’s macroeconomics with a telescope instead of a rear-view mirror.

5. Applications Go Far Beyond Finance

Yes, hedge funds and family offices are our primary clients today—but this technology applies to:

• Corporations deciding factory output, capital expenditures, or hiring

• Local governments validating growth or decline without waiting for state agencies

• Real estate investors identifying states or metros that are accelerating

• Supply chain operators monitoring industrial expansions

• Policymakers assessing regional development in real time

My favorite metaphor from the interview:

Whether you pay attention to the weather or not, it will still rain on you.

Atlas is simply offering you the umbrella first.

6. “Aren’t Satellite Images Public? Can Others Copy You?”

Yes, the imagery is public.
No, the algorithm is not.

Atlas filed patents in 2021 covering the ROY methodology—band math, feature extraction, spectral analysis, computer-vision architecture, and more patents are on the way.

As I told Barry:

Every Coke needs a Pepsi. But Pepsi still can’t crack Coke’s formula.

Competition will come. It should—this is a new field.
But Atlas has opened the frontier.

7. For Those Wondering About an Atlas Investment Fund…

People often ask whether we plan to launch an Atlas fund. While we sometimes use ‘Atlas Capital’ as a purely illustrative, non-commercial example, there is no fund today—and we do not trade on private signals that we don’t share with our clients. Instead, we use our proprietary signals combined with our economic and financial intuition to time the market.

If or when we explore a formal investment vehicle, it would be fully separate from our analytics business, and our readers would be the first to hear about it.

Subscribe now

8. Want to Follow the Data?

We publish:

• Quarterly GDP predictions (ahead of the BEA) — Free

• Weekly macro-market commentary — Premium

• Video explainers & deep dives — YouTube

• Custom consulting for corporations & funds — White glove

Follow along with us on socials:

• Substack

• YouTube

• Website

A Closing Thought

Macroeconomics is entering its “weather forecast moment.” For the first time, we can measure—not guess—the state of the economy in near-real time.

Satellite-powered forecasting is not the future.
It is the present.

And for those paying attention, it’s a serious advantage.

This article was written with valuable research assistance from Morgan Reppert, Executive Operations Associate for Atlas Analytics.

Refer a friend

Source: The Economist

As we wrote last week, market timing — long considered impossible — is now quantitatively achievable. Over the past year, Atlas Analytics generated a 54% return using ROY, our real-time GDP forecasting model that consistently outperforms the Federal Reserve’s own projections.

But the ability to forecast turning points does not mean that every period of elevated valuations represents a bubble ready to burst. In fact, distinguishing between early-stage mania, late-stage euphoria, and a true bubble endgame is one of the most difficult judgment calls in finance.

As The Economist recently put it:

“Even for the very best investors, identifying a bubble is easier than judging when it will burst.”

So, are we in an AI bubble?

We’re likely in the early innings of one — but that is very different from being at the end. Valuations are stretched, excitement is building, and narrative momentum is compounding, but the fundamental underpinnings of the economy remain strong. And as long as fundamentals anchor prices, bubbles can persist — sometimes for years.

That’s the paradox of early mania:
It looks like a bubble, it feels like a bubble, but it isn’t the bursting point.

So why hasn’t the bubble burst? The answer lies in the fundamentals.

Read more

Source: Atlas Analytics’ Schwab Account (Nov. 1, 2024 through Nov. 1, 2025)

Warren Buffett, the Sage of Omaha and one of the most prolific investors of all time, has an old saying:

“It’s not timing the market. It’s time in the market.”

Buffett was right for his era. But the signal revolution has changed the game.

Subscribe now

The Signal Revolution

What is the signal revolution?

It’s the shift from intuition-based investing to data-driven foresight — turning raw information into predictive signals.

Buffett’s era was about time in the market.
Our era is about timing the market using the signal.

Now, to be clear: long-term compounding still matters. Dividends, reinvestment, and the relentless math of compounding are as powerful as ever. Einstein even called compound interest, “man’s greatest invention.”

Where conventional wisdom goes wrong is in the antiquated belief that market timing is impossible.

As Atlas Analytics is now demonstrating in real time: market timing is not only possible — it’s profitable.

Message Jake Schneider

The Myth of Market Timing

The days of blind security selection devoid of information about the business cycle are over.

Using satellites constantly orbiting Earth, Atlas Analytics has created an algorithm that ingests the raw imagery to make predictions about U.S. (and eventually global) GDP growth rates.

Using these GDP nowcasts, which we currently have for Q4 (which we will publish in early January), we are able to use the “invisible tether” between economic activity and financial markets to create price targets for the equity markets.

When financial prices are below these targets, we buy; when they are above, we sell (and even sell short).

For most of this year, we bought, including after Trump’s re-election conventional wisdom said to sell, citing tariffs, the war in Ukraine, and economic uncertainty.

For the past few weeks, the financial markets have soured as predicted two months ago in our post, Mr. Market is now over his skis.

Now we’re going long again as the equity markets are currently under-valued.

Learn More

Atlas Analytics vs. the Market

The Result: Atlas Analytics’ portfolio is up 54% since November 2024.

This is not a fluke or an accident. This is proof that market timing is not only possible; it’s lucrative.

Why Atlas Analytics Is Different

Every professional investor I’ve spoken to (and I speak to a lot lately) has said the same thing: the alternative-data space is crowded, and most claims of alpha don’t hold up. I agree with them: 99% of these products are noise. That’s why I built Atlas Analytics differently.

Source: Atlas Analytics’ Schwab Account (Nov. 1, 2024 through Nov. 1, 2025)

I’ve been trading live on Atlas Analytics’ model for the past year and a half. The results so far: Since November 2024, our portfolio is up +53.75% with an annualized volatility of 24.68% and a Sharpe ratio of 2.03. This isn’t back tested; this is capital at risk.

What is the Sharpe ratio? As a measure of risk to return (total gain less the risk-free rate divided by portfolio standard deviation), it denotes how effective an investor is at generating gains per unit of risk.

Basically, a Sharpe above 1 is good, above 2 is great, and above 3 is exceptional. Most profitable hedge funds aim for a Sharpe ratio between 1.5 and 2.5. Atlas Analytics, at 2.03, is already in hedge-fund quality territory, and we’re just getting started.

Institutions want to see a long, consistent track record. I’m building that quarter by quarter, with the same rigor a fund would use, so the persistence becomes clear over time.

Satellite imagery is abundant. What differentiates Atlas is the platform we’ve built that turns raw pixels into usable macroeconomic indicators at scale. The value is in an automated system that delivers consistent, reliable macro signals clients can use directly.

Atlas is building a track record that strengthens every quarter. As the results compound, the question naturally shifts to scale and impact.

For decades, the consensus was that market timing was impossible. With Atlas Analytics, that consensus is crumbling. The only real question now is: how far can we go? I invite you to join the debate, and the journey.

Leave a comment

Bonus Content for Our Premium Subscribers

What We’re Seeing Now: A Preview of Q4 and Its Equity-Market Implications

Every quarter, Atlas Analytics updates its GDP nowcast using the latest satellite imagery, and geospectral signatures embedded in the Landsat program. Although our full Q4 estimate will be released in early January, our in-progress read on the quarter is already clear enough to guide positioning.

Read more

TLDR:

• Across 14 quarters of state-level analysis, Atlas ROY reveals a powerful insight: economic geography leaves a measurable spectral footprint.

• States with clear physical activity, such as construction, energy, transportation, agriculture, show the strongest correlations with official GDP, while tech- and finance-heavy regions leave weaker or even inverted signals.

• These differences form “Unique Geospectral Signatures for Economic Geography”, our term for how each region’s built and vegetative environment interacts with economic output.

• The implication is profound: understanding these signatures may help explain not just why states diverge, but how entire economies develop.

What the Picture Says about Economic Geography

As we said before: A picture is worth a thousand words.

In part one of this three-part series, we explored how Atlas Analytics’ proprietary algorithm, ROY, works and what its capabilities are.

In Part II, we explore how Atlas Analytics’ GDP forecasts perform across the United States in comparison to the Bureau of Economic Analysis (BEA) official numbers, and what exactly that means for the U.S. economy.

In this article, we build towards something deeper and even profound: the discovery that every region leaves a unique geospectral signature, a distinct physical fingerprint that reveals how its economy grows, evolves, and behaves in real time.

This has important implications not only for the U.S., but for the economic development of every community and country around the world.

That’s Where Atlas Comes In

In last week’s article “The Road Ahead,” we discussed the ramifications of the government shutdown and how we still have no official visibility into Q3 economic activity, let alone Q4 (which is now more than half way over).

Government-produced GDP is slow, retrospective, and doesn’t tell us what is happening in real-time, and honestly, who has time for that in this economy.

That’s where Atlas Analytics comes in.

Using Atlas’ ROY, we can evaluate predictive strength across all states for the past 14 quarters, identifying where the model is most reliable, why it works best in certain regions, and what these patterns reveal about the structure of the U.S. economy itself.

This has an important implication: If we can understand where the model has worked well, we can gain insight about what it’s telling us for our predictions.

We will break down such predictions applied to all 50 U.S. states plus Washington D.C., comparing Atlas’ real-time satellite estimates to the official BEA GDP data, and what those patterns say about real-time economic activity.

A National Headshot

The heat map above represents the correlation between Atlas’ GDP predictions by state compared to the BEA’s GDP data between 2022 Quarter 1 and 2025 Quarter 2 (14 periods).

ROY is consistently most accurate in the Mountain West and the Central U.S., where correlations reach 0.42–0.46 regionally. ROY picks up real change here and matches GDP movements with impressive precision.

And what about the best performing states?

Interestingly, they are the more rural states ranging from Nevada in the west to Arkansas in the middle to New Hampshire in the north.

What the Patterns Reveal Across the Four Key Clusters

On a macro level, the U.S. is not just one economy: it is an amalgamation of regional agglomerations and ROY’s data is a mirror of that economic reality.

From our analysis, we view the predictions in the following four clusters:

1. Central States: AL, AR, IA, KS, KY, LA, MN, MS, MO, NE, ND, OK, SD, TN, TX

2. Coasts: AK, CA, CT, DE, DC, FL, GA, HI, ME, MD, MA, NH, NJ, NY, NC, OR, PA, RI, SC, VT, VA, WA, WV

3. Industrial Midwest: IL, IN, MI, OH, WI

4. Mountain West: AZ, CO, ID, MT, NV, NM, UT, WY

From a bird’s eye view, these maps below demonstrate both our prediction accuracy (RMSE) and precision (correlation)1:

With an average RMSE across all states of 3.5 and an average correlation of 0.3, Atlas predictions are often more accurate than the BEA’s own stated revision rate of 1.2 percentage points2.

We know ROY is exceptionally accurate where the economy is spatially visible, so we will continue to target regional versioning and variant testing to strengthen our forecasting in areas that are more complex.

Why Some Geographies Perform Well

Why does the Central U.S. perform best, while the neighboring Mountain West shows the lowest RMSE?

Why does Nevada exhibit our highest correlation, while California, the world’s fourth-largest economy, sits near the bottom?3

At a high level, the answer is simple: ROY performs best where the physical economy is tightly linked to economic output.

But the details matter:

• The built environment is a weaker proxy for tech- or finance-driven GDP. Regions dominated by software, financial markets, biotech, and intangible services generate massive economic output with little visible physical change. Satellites excel at detecting infrastructure, logistics, and construction, but these sectors leave faint spatial footprints.

• Housing dynamics vary dramatically across states.
  In some regions, housing markets track employment, migration, and investment flows very closely; in others, the signal is noisy, reactive, or distorted by supply constraints. Where housing behaves like a clean leading indicator, ROY performs well. Where it does not, correlations weaken.

• Manufacturing-heavy states experience sharp, cyclical shocks.
  Inventory swings, supply chain disruptions, auto production cycles, and plant downtime can produce sudden changes in output that may not register immediately in the built environment. ROY may pick up the direction correctly while missing the magnitude or timing.

• Economic complexity creates blind spots.
  States with diversified or hybrid economies, mixing heavy industry with digital services, can produce conflicting signals, especially when one sector is booming while another contracts.

In short, regions with clear, continuous physical activity (energy, logistics, construction, transportation, agriculture, and industrial infrastructure) give ROY clean, high-fidelity signals. Regions dominated by intangible activity do not.

And that’s exactly why we do this work.

Atlas’ ROY model is a work in progress: improving, adapting, and learning every day as the U.S. economy evolves.

A Unique Geospectral Signature for Economic Geography

Each state interacts with the physical world in its own distinct way.

Construction patterns, industrial activity, and crop cycles all leave unique geospectral fingerprints in the satellite record, but states respond to these signals on different timelines.

Some geographies show long lags before physical change appears in economic statistics. Others exhibit surprising vegetation relationships, including occasional negative correlations, where increases in greenness coincide with economic slowdowns or vice-versa.

Why?

Our working hypothesis is that each geography blends its built environment, land use, and vegetative patterns differently, producing distinct spectral signatures that map onto local economic structures.

We call these Unique Geospectral Signatures for Economic Geography.

Understanding these signatures may help explain patterns of economic development writ large for global sustainable growth.

The Common Thread

What do the above patterns reveal about ROY’s GDP accuracy?

• Rural states tend to have stable, structurally consistent economies — industries that evolve gradually and predictably over time.

• They exhibit strong physical signals in the built environment: construction, infrastructure, transportation corridors, energy activity, and land-use patterns that satellites can track with precision.

• They contain fewer “noise” variables from sectors like finance, software, or other intangible-output industries that leave little physical footprint.

• And critically, they are not major financial trading hubs or “undetectable” technology hubs, where GDP growth is often decoupled from visible physical activity.

This common thread explains the broader regional patterns we see when we analyze the entire country through four distinct economic clusters. Taken together, these characteristics sharpen ROY’s visibility and allow the algorithm to excel where the real economy is spatially observable.

Where the real economy is spatially observable, ROY excels.

This common thread also explains the broader regional patterns we see when we analyze the entire country through four distinct economic clusters.

The Evolving Economic Landscape

That’s a wrap for Part II. In Part III, we will explore a time-series evolution of our state-level GDP forecasts versus the BEA, and what that portends for future economic development across the United States.

Curious to see the specs on your state?

Message Me

Want our current state-level or national forecasts for Quarter 3 and Quarter 4? Contact us for a commercial, academic, and or institutional subscription.

Subscribe now

This article was written with valuable research assistance from Morgan Reppert, Executive Operations Associate for Atlas Analytics.

It’s almost Thanksgiving and remarkably, we still don’t have any official visibility into Q3 economic activity.

Not for July.
Not for August.
Not for September.

The longest government shutdown in U.S. history ended on Wednesday, and yet it will still likely be weeks (if not months) before we have true visibility for Q3, let alone a preliminary look at Q4.

Yes, the government has reopened, but America’s economic dashboard is still dark.

Where We Really Stand Today

Here’s the short answer: we still don’t know what happened in Q3.

Not because the data doesn’t exist but because the agencies that publish it are still digging out from the shutdown.

1. We still don’t have trade numbers from the Census Bureau.

Trade accounts for a massive share of quarterly GDP variation and the last update from the Census Bureau was for July. Thus, August, September and October cargo volumes, container flows, port activity are all frozen behind the shutdown backlog. Without this, economists are flying blind on net exports.

2. We don’t have the jobs numbers from the BLS.

Employment is the pulse of the U.S. economy and right now, that pulse monitor is still unplugged. No nonfarm payrolls, no household data, no revisions.

3. We don’t know when we’ll get the first GDP release from the BEA.

Normally, by this point in November, we’d have the Advance Estimate for Q3 2024 (it was originally scheduled to be released on October 30).

Instead, we have…

4. A short update from the BEA.

The translation: they’re working through the backlog, but there’s no clear timeline for catching up, not to mention providing full revisions.

Why This Matters

When official data shuts down, the markets don’t stop. Investors still trade. Companies still hire. States still make budget decisions. Households still spend. The economy keeps moving, even when the measurement system doesn’t.

This is exactly the problem Atlas was built to solve.

How Atlas Sees Q3

On October 26 Atlas released our Q3 2025 GDP forecast. As a reminder, here’s how we saw the U.S. economy at that point:

While the government remains in catch-up mode, Atlas’ real-time indicators have already processed the entire summer and early fall and we believe headline GDP remains strong at approximately ~2.4%.

Since then, we have been updating Q3 and even Q4 for all components (Core GDP, Net Exports and Private Inventories) every single week for our clients.

From our data, Q3 wasn’t a mystery. It was visible weeks ago.

One Step Forward, One Step Back

The government is back online, but the data lags won’t resolve overnight. The shutdown created a time gap that can’t be compressed, and that means:

• Markets will continue to be trading blind for weeks to come.

• Businesses will be operating without official benchmark data.

• Most GDP estimates will rely on inference, not measurement, especially since we suspect the BEA will have limited ability to produce all three estimates for Q3 and possibly for Q4.

Atlas will continue to bridge that gap.

A Closing Thought

It’s strange to be entering the holiday season without knowing what happened in the economy months ago. But this moment makes one thing clear:

Economic intelligence shouldn’t grind to a halt when the government does.

We’ll keep providing clarity as the official numbers slowly return.

Technical Appendix (Premium Subscribers Only)

How Atlas Measured Q3 While Washington Was Dark

This appendix outlines the methodology behind Atlas Analytics’ real-time estimates during the 2025 government shutdown, including data inputs, model behavior, and uncertainty considerations.

Subscribe now

Read more