On the Directional Predictability of Equity Premium Using Machine Learning Techniques

This paper applies a plethora of machine learning techniques to forecast the direction of the U.S. equity premium. Our techniques include benchmark binary probit models, classification and regression trees (CART), along with penalized binary probit models. Our empirical analysis reveals that the sophisticated machine learning techniques significantly outperformed the benchmark binary probit forecasting models, both statistically and economically. Overall, the discriminant analysis classifiers are ranked first among all the models tested. Specifically, the high dimensional discriminant analysis (HDDA) classifier ranks first in terms of statistical performance, while the quadratic discriminant analysis (QDA) classifier ranks first in economic performance. The penalized likelihood binary probit models (Least Absolute Shrinkage and Selection Operator, Ridge, Elastic Net) also outperformed the benchmark binary probit models, providing significant alternatives to portfolio managers.