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,...

Portfolio optimization focuses on risk and return prediction, yet implementation costs critically matter. Predicting trading costs is challenging because costs depend on trade size and trader identity, thus impeding a generic solution. We focus on a component of trading costs that applies...

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...

The core statistical technology in artificial intelligence is the large-scale transformer network. We propose a new asset pricing model that implants a transformer in the stochastic discount factor. This structure leverages conditional pricing information via cross-asset information sharing and...

In a model with multiple Pareto-ranked equilibria we add trade in assets that pay based on the realization of a sunspot. Asset trading restricts the equilibrium set in a way that raises welfare by eliminating equilibria with a high likelihood of disasters. When the probability of a disaster is...

We identify different roles traders play using data with trader identities for all transactions in SENSEX-index stocks on the Bombay Stock Exchange from January 2005 to December 2011. Individual day traders (IDT) are identified as "noise traders", who play an important role in the market...

We analyze cross-sectional and time series information from forty-seven equity markets around the world, to consider whether short-sales restrictions affect the efficiency of the market, and the distributional characteristics of returns to individual stocks and market indices. Using the approach...

There have been enormous differences of opinion between U.S. and Japanese institutional investors about the outlook for stock prices, differences across the two countries in average one-year-ahead forecasts for the Japanese stock market as great as twenty percentage points. In the past two years...

Optimal investment of firms implies that expected stock returns are tied with the expected marginal benefit of investment divided by the marginal cost of investment. Winners have higher expected growth and expected marginal productivity (two major components of the marginal benefit of...

The extant literature predicts market returns with "simple" models that use only a few parameters. Contrary to conventional wisdom, we theoretically prove that simple models severely understate return predictability compared to "complex" models in which the number of parameters exceeds the...