Machine Learning in Systematic Equity Allocation: A Model Comparison

Abstract

Recent criticisms suggest that Machine Learning-based approaches only suit predicting very short-term price movements. Tony Guida and Guillaume Coqueret apply well-known ML algorithms to systematic equity investment, presenting a methodology which features a critical stage of feature and label engineering, a step that helps uncover hidden structures in the equity market space. Only then, the authors argue, can a modern quantitative approach make accurate long-term predictions.