Deep Learning for Forecasting Stock Returns in the Cross-Section

TL;DR

This paper demonstrates that deep neural networks outperform shallow networks and traditional models in predicting one-month-ahead stock returns in the Japanese market, highlighting deep learning's potential in financial forecasting.

Contribution

It applies deep learning to cross-sectional stock return prediction and compares its performance with shallow networks and other machine learning models.

Findings

Deep neural networks outperform shallow networks.

Deep learning models outperform traditional machine learning models.

Deep learning shows promise for stock return prediction.

Abstract

Many studies have been undertaken by using machine learning techniques, including neural networks, to predict stock returns. Recently, a method known as deep learning, which achieves high performance mainly in image recognition and speech recognition, has attracted attention in the machine learning field. This paper implements deep learning to predict one-month-ahead stock returns in the cross-section in the Japanese stock market and investigates the performance of the method. Our results show that deep neural networks generally outperform shallow neural networks, and the best networks also outperform representative machine learning models. These results indicate that deep learning shows promise as a skillful machine learning method to predict stock returns in the cross-section.