Big Loans to Small Businesses: Predicting Winners and Losers in an Entrepreneurial Lending Experiment
American Economic Review, 2024

Bryan, Gharad; Karlan, Dean; Osman, Adam
We experimentally study the impact of relatively large enterprise loans in Egypt. Larger loans generate small average impacts, but machine learning using psychometric data reveals "top performers" (those with the highest predicted treatment effects) substantially increase profits, while profits drop for poor performers. The large differences imply that lender credit allocation decisions matter for aggregate income, yet we find existing practice leads to substantial misallocation. We argue that some entrepreneurs are overoptimistic and squander the opportunities presented by larger loans by taking on too much risk, and show the promise of allocations based on entrepreneurial type relative to firm characteristics.

Belief Distortions and Macroeconomic Fluctuations
American Economic Review, 2022

Bianchi, Francesco; Ludvigson, Sydney C.; Ma, Sai
This paper combines a data-rich environment with a machine learning algorithm to provide new estimates of time-varying systematic expectational errors (belief distortions) embedded in survey responses. We find sizable distortions even for professional forecasters, with all respondent-types overweighting the implicit judgmental component of their forecasts relative to what can be learned from publicly available information. Forecasts of inflation and GDP growth oscillate between optimism and pessimism by large margins, with belief distortions evolving dynamically in response to cyclical shocks. The results suggest that artificial intelligence algorithms can be productively deployed to correct errors in human judgment and improve predictive accuracy.

From Mad Men to Maths Men: Concentration and Buyer Power in Online Advertising
American Economic Review, 2021

Decarolis, Francesco; Rovigatti, Gabriele
This paper analyzes the impact of intermediary concentration on the allocation of revenue in online platforms. We study sponsored search documenting how advertisers increasingly bid through a handful of specialized intermediaries. This enhances automated bidding and data pooling, but lessens competition whenever the intermediary represents competing advertisers. Using data on nearly 40 million Google keyword auctions, we first apply machine learning algorithms to cluster keywords into thematic groups serving as relevant markets. Using an instrumental variable strategy, we estimate a decline in the platform's revenue of approximately 11 percent due to the average rise in concentration associated with intermediary merger and acquisition activity.

Artificial Intelligence, Algorithmic Pricing, and Collusion
American Economic Review, 2020

Calvano, Emilio; Calzolari, Giacomo; Denicolo, Vincenzo; Pastorello, Sergio
Increasingly, algorithms are supplanting human decision-makers in pricing goods and services. To analyze the possible consequences, we study experimentally the behavior of algorithms powered by Artificial Intelligence (Q-learning) in a workhorse oligopoly model of repeated price competition. We find that the algorithms consistently learn to charge supracompetitive prices, without communicating with one another. The high prices are sustained by collusive strategies with a finite phase of punishment followed by a gradual return to cooperation. This finding is robust to asymmetries in cost or demand, changes in the number of players, and various forms of uncertainty.

Predicting and Understanding Initial Play
American Economic Review, 2019

Fudenberg, Drew; Liang, Annie
We use machine learning to uncover regularities in the initial play of matrix games. We first train a prediction algorithm on data from past experiments. Examining the games where our algorithm predicts correctly, but existing economic models don't, leads us to add a parameter to the best performing model that improves predictive accuracy. We then observe play in a collection of new "algorithmically generated" games, and learn that we can obtain even better predictions with a hybrid model that uses a decision tree to decide game-by-game which of two economic models to use for prediction.

The Mortality and Medical Costs of Air Pollution: Evidence from Changes in Wind Direction
American Economic Review, 2019

Deryugina, Tatyana; Heutel, Garth; Miller, Nolan H.; Molitor, David; Reif, Julian
We estimate the causal effects of acute fine particulate matter exposure on mortality, health care use, and medical costs among the US elderly using Medicare data. We instrument for air pollution using changes in local wind direction and develop a new approach that uses machine learning to estimate the life-years lost due to pollution exposure. Finally, we characterize treatment effect heterogeneity using both life expectancy and generic machine learning inference. Both approaches find that mortality effects are concentrated in about 25 percent of the elderly population.

Does Machine Learning Automate Moral Hazard and Error?
American Economic Review, 2017

Mullainathan, Sendhil; Obermeyer, Ziad
Machine learning tools are beginning to be deployed en masse in health care. While the statistical underpinnings of these techniques have been questioned with regard to causality and stability, we highlight a different concern here, relating to measurement issues. A characteristic feature of health data, unlike other applications of machine learning, is that neither y nor x is measured perfectly. Far from a minor nuance, this can undermine the power of machine learning algorithms to drive change in the health care system--and indeed, can cause them to reproduce and even magnify existing errors in human judgment.

Wearable Technologies and Health Behaviors: New Data and New Methods to Understand Population Health
American Economic Review, 2017

Handel, Benjamin; Kolstad, Jonathan
We study a randomized control trial in a large employer population of access to "wearable" technologies and the associated planning and monitoring tools on improved health behaviors (sleep and exercise). Both ITT and IV estimates based on actual plan enrollment for the treatment group suggest statistically significant but economically small changes in behavior after three months. We then implement machine learning-based models to assess treatment effect heterogeneity. We find little evidence for heterogeneous treatment effects base on observables. We also present detailed data on sleep patterns underscoring the value of this new data source to researchers.

Double/Debiased/Neyman Machine Learning of Treatment Effects
American Economic Review, 2017

Chernozhukov, Victor; Chetverikov, Denis; Demirer, Mert; Duflo, Esther; Hansen, Christian; Newey, Whitney
Chernozhukov et al. (2016) provide a generic double/de-biased machine learning (ML) approach for obtaining valid inferential statements about focal parameters, using Neyman-orthogonal scores and cross-fitting, in settings where nuisance parameters are estimated using ML methods. In this note, we illustrate the application of this method in the context of estimating average treatment effects and average treatment effects on the treated using observational data.

Productivity and Selection of Human Capital with Machine Learning
American Economic Review, 2016

Chalfin, Aaron; Danieli, Oren; Hillis, Andrew; Jelveh, Zubin; Luca, Michael; Ludwig, Jens
Economists have become increasingly interested in studying the nature of production functions in social policy applications, with the goal of improving productivity. Traditionally models have assumed workers are homogenous inputs. However, in practice, substantial variability in productivity means the marginal productivity of labor depends substantially on which new workers are hired--which requires not an estimate of a causal effect, but rather a prediction. We demonstrate that there can be large social welfare gains from using machine learning tools to predict worker productivity, using data from two important applications - police hiring and teacher tenure decisions.