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 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...

We argue that comprehensive out-of-sample (OOS) evaluation using statistical decision theory (SDT) should replace the current practice of K-fold and Common Task Framework validation in machine learning (ML) research. SDT provides a formal framework for performing comprehensive OOS evaluation...

We provide evidence for a causal link between the US economy and the global financial cycle. Using intraday data, we show that US macroeconomic news releases have large and significant effects on global risky asset prices. Stock price indexes of 27 countries, the VIX, and commodity prices all...

Savings increasingly flow to low-cost index funds, which simply buy and hold the stocks in a major index, such as the S&P 500. Increased indexing impedes incorporation of idiosyncratic information into stock prices. We limit endogeneity bias by showing that exogenous idiosyncratic currency...

Neural networks offer a promising tool for the analysis of nonlinear economies. In this paper, we derive conditions for the global stability of nonlinear rational expectations equilibria under neural network learning. We demonstrate the applicability of the conditions in analytical and numerical...

We decompose the squared VIX index, derived from US S&P500 options prices, into the conditional variance of stock returns and the equity variance premium. The latter is increasing in risk aversion in a wide variety of economic settings. We tackle several measurement issues assessing a plethora...

A growing literature uses the Russell 1000/2000 reconstitution event as an identification strategy to investigate corporate finance and asset pricing questions. To implement this identification strategy, researchers need to approximate the ranking variable used to assign stocks to indexes. We...

We apply deep learning to daytime satellite imagery to predict changes in income and population at high spatial resolution in US data. For grid cells with lateral dimensions of 1.2km and 2.4km (where the average US county has dimension of 55.6km), our model predictions achieve R2 values of 0.85...

A forecasting comparison is undertaken in which 49 univariate forecasting methods, plus various forecast pooling procedures, are used to forecast 215 U.S. monthly macroeconomic time series at three forecasting horizons over the period 1959 - 1996. All forecasts simulate real time implementation,...