We theoretically characterize the behavior of machine learning asset pricing models. We prove that expected out-of-sample model performance--in terms of SDF Sharpe ratio and test asset pricing errors--is improving in model parameterization (or "complexity"). Our empirical findings verify the...

We propose a statistical model of differences in beliefs in which heterogeneous investors are represented as different machine learning model specifications. Each investor forms return forecasts from their own specific model using data inputs that are available to all investors. We measure...

This paper studies the predictability of ultra high-frequency stock returns and durations to relevant price, volume and transactions events, using machine learning methods. We find that, contrary to low frequency and long horizon returns, where predictability is rare and inconsistent,...

We investigate the economic consequences of statistical learning for arbitrage pricing in a high-dimensional setting. Arbitrageurs learn about alphas from historical data. When alphas are weak and rare, estimation errors hinder arbitrageurs--even those employing optimal machine learning...

Missing data for return predictors is a common problem in cross sectional asset pricing. Most papers do not explicitly discuss how they deal with missing data but conventional treatments focus on the subset of firms with no missing data for any predictor or impute the unconditional mean. Both...

We survey the nascent literature on machine learning in the study of financial markets. We highlight the best examples of what this line of research has to offer and recommend promising directions for future research. This survey is designed for both financial economists interested in grasping...

Markets, likened to an invisible hand, often appear to contradict econometric assumptions that rule out spillovers of one person's treatment on another's outcomes. This paper provides a simple statistical framework highlighting that controls are indirectly affected by the treatment through the...

A recent econometric literature shows two distinct paths for identification with shift-share instruments, leveraging either many exogenous shifts or exogenous shares. We present the core logic of both paths and practical takeaways via simple checklists. A variety of empirical settings illustrate...

This paper proposes a method to estimate treatment effects in difference-in-differences designs in which the treatment start is staggered over time and treatment effects are heterogeneous by group, time, and covariates, and when the data are repeated cross-sections. We show that a...

We document substantial racial disparities in consumer bankruptcy outcomes and investigate the role of racial bias in contributing to these disparities. Using data on the near universe of US bankruptcy cases and self-reported and manually-identified measures of race, we show that minority filers...