Paul E. Soto

Economist

Welcome! I am a principal economist in the Industrial Output Section at the Federal Reserve Board of Governors in Washington, D.C. My research develops high-frequency economic indicators from unstructured data using AI/ML techniques, with applications to financial intermediation, manufacturing, productivity, and labor markets. This work improves real-time measurement of economic and financial conditions, including uncertainty, investment dynamics, supply chain disruptions, and bank behavior. My research has been published in leading academic journals such as Management Science, the Journal of International Economics, and the Journal of Applied Econometrics, and has been featured in the Financial Times, Fortune, and speeches by Federal Reserve officials.

Paul E. Soto

Research

Banking & Macroeconomics

Stressed Banks? Evidence from the Largest-Ever Supervisory Review

with Puriya Abbassi, Rajkamal Iyer, and José-Luis Peydró

Management Science, 2025

We use the ECB's Asset Quality Review as a natural experiment, showing that banks temporarily reduce risk by shifting portfolios toward safer assets for supervisory compliance, but revert afterward, causing persistent negative real effects, particularly harming high-risk firms.

View Paper

Capital Controls, Domestic Macroprudential Policy and the Bank Lending Channel of Monetary Policy

with Andrea Fabiani, Martha López Piñeros, and José-Luis Peydró

Journal of International Economics, 2022

We examine how the simultaneous implementation of capital controls and domestic reserve requirements in Colombia during a credit boom effectively curtailed banks' risky lending practices, and show that these policies complementarily strengthened the transmission of monetary policy to credit supply by limiting foreign currency arbitrage and domestic funding, ultimately reducing financial vulnerability.

View Paper

Capital Controls, Corporate Debt and Real Effects

with Andrea Fabiani, Martha López Piñeros, and José-Luis Peydró

The Review of Financial Studies, Conditionally Accepted

We examine Colombia's foreign-debt capital controls using firm-level data, finding that these controls limit risky foreign borrowing during booms, thus safeguarding exports and employment during crises, especially benefiting financially constrained firms.

View Paper

Trademarks in Banking

with Ryuichiro Izumi and Antonis Kotidis

Finance and Economics Discussion Series, 2024

We study how trademark similarity among banks significantly increases deposit withdrawals following bank failures, particularly when media coverage is extensive, highlighting the underestimated role of trademarks in financial contagion and banking stability.

View Paper

AI & Natural Language Processing in Economics

Generative AI at the Crossroads: Light Bulb, Dynamo, or Microscope?

with Martin N. Baily, David M. Byrne, and Aidan T. Kane

American Economic Association Papers and Proceedings, Forthcoming

We assess the extent to which genAI is poised to be a general-purpose technology and invention of a method of invention, specifically whether it primarily raises productivity levels, growth rates, or the efficiency of innovation.

Featured in Fortune, August 1, 2025

Working Paper

Manufacturing Sentiment: Forecasting Industrial Production with Text Analysis

with Tomaz Cajner, Leland D. Crane, Christopher Kurz, Norman Morin, and Betsy Vrankovich

Journal of Applied Econometrics, Forthcoming

We show that NLP techniques, including transformer-based deep learning models, applied to purchasing managers' textual survey responses significantly enhance forecasting accuracy of U.S. industrial production.

View Paper

Inside the Boardroom: Evidence from the Board Structure and Meeting Minutes of Community Banks

with Rosalind L. Bennett and Manju Puri

Journal of Banking & Finance, Revision Requested

We analyze unique board-meeting records from community banks, showing that during financial distress boards shift discussions from routine activities toward capital management and regulatory oversight, and experience increased turnover and sharply negative sentiment.

View Paper

Breaking the Word Bank: Measurement and Effects of Bank Level Uncertainty

Journal of Financial Services Research, 2021

I use NLP methods on bank earnings calls to measure idiosyncratic uncertainty to show that higher uncertainty significantly reduces lending and increases liquidity, particularly during volatile economic conditions, directly impacting broader credit availability.

View Paper

Total Recall? Evaluating the Macroeconomic Knowledge of Large Language Models

with Leland D. Crane and Akhil Karra

Finance and Economics Discussion Series, 2025

We evaluate how well LLMs recall historical macro data and data release dates. We find that LLMs can mix first-print values with later revisions and blend information across reference periods, potentially introducing look-ahead bias in pseudo-real-time analysis.

View Paper

Research in Commotion: Measuring AI Research and Development through Conference Call Transcripts

Finance and Economics Discussion Series, 2025

I develop the AIR Index—a novel NLP-based measure from earnings calls—to quantify AI R&D at the firm level, and show that AI R&D leads to immediate market valuation gains and accelerated capital expenditures without immediate productivity increases.

View Paper

Tracking Real Time Layoffs with SEC Filings: A Preliminary Investigation

with Leland D. Crane, Emily Green, Molly Harnish, Will McClennan, Betsy Vrankovich, and Jacob Williams

Finance and Economics Discussion Series, 2024

We develop a real-time indicator of layoffs using SEC 8-K filings analyzed through NLP and LLMs, which provides timely signals that correlate strongly with labor market conditions.

View Paper

Policy Notes

Pro-Productivity Policies for the U.S. Economy

with Martin N. Baily, David M. Byrne, and Aidan T. Kane

Productivity Institute Insights Paper, 2025

We examine the sources of U.S. productivity leadership, focusing on innovation, business dynamism, and the adoption of new technologies. We also discuss the role of AI, competition policy, capital formation, and labor market adjustments.

View Paper

Measuring AI Uptake in the Workplace

with Leland D. Crane and Michael Green

FEDS Notes, 2024

We review multiple firm and employee surveys, revealing that as of 2025 AI adoption varies widely but consistently falls within a 20-40% range.

Featured in speech by Vice Chair for Supervision Michael S. Barr, Feb 18, 2025

Featured in Speech by Governor Adriana D. Kugler, Feb 7, 2025

View Paper

Measurement and Effects of Supply Chain Bottlenecks Using Natural Language Processing

FEDS Notes, 2023

I develop the Supply Chain Bottleneck Sentiment (SCB Sentiment) index, a novel NLP-based measure derived from Federal Reserve Beige Books, capturing both frequency and sentiment of supply chain disruptions.

Featured in Financial Times, March 11, 2025

Featured in Remarks from Vice Chair Philip N. Jefferson, Feb 21, 2025

View Paper

About Me

I am a principal economist at the Federal Reserve Board, having joined in 2022. In the Industrial Output section, I work on economic measurement, including the estimation of U.S. industrial production and capacity utilization (the G.17), which covers manufacturing, mining, and utilities. I also contribute to the Federal Reserve Board's Expanded Measurement Agenda where I use ML/AI techniques and novel data sources to develop high-frequency measures of economic activity. In addition, I am a Research Fellow at the Federal Deposit Insurance Corporation. Previously, from 2018-2022, I was a financial economist at the FDIC, where I conducted banking research and developed quantitative models to support FDIC operations. While working at the FDIC and the Fed, I taught courses in Text Mining and Financial Analytics as an adjunct professor at the University of Maryland from 2019 to 2023.

I received my PhD in Economics from Universitat Pompeu Fabra (the Barcelona School of Economics) in 2018, and hold a B.A. in Applied Mathematics from the University of California, Berkeley. During my doctoral studies, I worked closely with various central banks, including an eight-month research visit at the Deutsche Bundesbank and research projects with the Banco de la República of Colombia. Earlier in my career, I held roles in credit analytics at Moody's Analytics and in investment management.

Outside of economics and finance, I am actively involved in artificial intelligence, Brazilian Jiu Jitsu, and live performance, including improv and theater.

Download CV Federal Reserve Board Profile Google Scholar