The Term Structure of Machine Learning Alpha

Machine learning (ML) models for predicting stock returns are typically trained on one-month forward returns. Although 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, the authors 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. The authors conclude that design choices are critical for the success of ML models in real-life applications.