The Term Structure of Machine Learning Alpha

Abstract

Machine learning (ML) models for predicting stock returns are typically trained on one-month forward returns. While these models show impressive full-sample gross alphas, their performance net of transaction costs post 2004 is close to zero. By training on longer prediction horizons and using efficient portfolio construction rules, we demonstrate that ML-based investment strategies can still yield significant positive net returns. Longer-horizon strategies select slower signals and load more on traditional asset pricing factors but still unlock unique alpha. We conclude that design choices are critical for the success of ML models in real-life applications.

Keywords: machine learning, asset pricing, factor investing, alpha, investment strategies, trading costs

JEL Classification: G10, G12, G17