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...

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 present an alternative expectation formation mechanism that helps rationalize well known asset pricing anomalies, such as the predictability of excess returns, excess volatility, and the equity-premium puzzle. As with rational expectations (RE), the expectation formation mechanism we consider...

Volatility permeates modern financial theories and decision making processes. As such, accurate measures and good forecasts of future volatility are critical for the implementation and evaluation of asset pricing theories. In response to this, a voluminous literature has emerged for modeling the...

The equity variance risk premium is the expected compensation earned for selling variance risk in equity markets. The variance risk premium is positive and shows moderate persistence. High variance risk premiums coincide with the left tail of the consumption growth distribution shifting down....

If investors are myopic mean-variance optimizers, a stock's expected return is linearly related to its beta in the cross section. The slope of the relation is the cross-sectional price of risk, which should equal the expected equity premium. We use this simple observation to forecast the...

Our paper reexamines the forecasting regressions which predict annual aggregate stock market returns net of the risk-free rate with lagged aggregate dividend-yield ratios and dividend-price ratios. Prior to 1990, the conditional dividend yield could reliably outperform the historical equity...

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...

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 and test a novel economic mechanism that generates stock return predictability on both the time series and the cross section. In our model, investors' income has two sources, wages and dividends, that grow stochastically over time. As a consequence, the fraction of total income...