Performance Attribution of Machine Learning Methods for Stock Returns Prediction

Recently many research articles have focused on the prediction of stock returns using machine learning methods. All show that regression trees and neural networks have superior predicting power than linear models. In this paper we analyze the performance of investable portfolios built using predicted stock returns and attribute their performance to linear, marginal nonlinear and interaction effects. We use a large set of features including pricebased, fundamental-based, and sentiment-based descriptors and use model averaging to get robust out-of-sample predictions. We find that the superiority of regression trees and neural networks comes from two points: their strong regularization mechanism and their capacity to capture interaction effects. The non-linear component of the marginal predictions on the other hand has no predictive power. Thanks to our methodology, we manage to isolate and study in details the interaction component. We find that it has significative long term performance independent from the linear modeling and is stable through time