2021/08/04 by Yang Bai, Kuntara Pukthuanthong, Bai, Yang +1
Decision Sciences · Economics, Econometrics and Finance · #Computational Finance (q-fin.CP) #FOS: Computer and information sciences #FOS: Economics and business #Financial Markets and Investment Strategies #General Economics (econ.GN) #General Finance (q-fin.GN) #Machine Learning (cs.LG) #Market Dynamics and Volatility #Portfolio Management (q-fin.PM) #Stock Market Forecasting Methods
paper · pdf · doi:10.48550/arxiv.2108.02283
openalex publication_date 2021/08/04 · openalex created_date 2021/08/16 · openalex updated_date 2026/07/28
Classification outperforms regression across matched machine learning models in portfolio construction. A stacking ensemble of gradient boosted tree, random forest, and neural network yields a value-weighted annualized Sharpe ratio of 1.83 for classification and 1.11 for regression. This outperformance persists in multiclass settings, across subsamples, and after transaction costs. Spanning tests show that classification retains economically large alphas after we control for regression, whereas regression alphas shrink substantially once we control for classification. These results indicate that classification extracts more return information than matched regression. Our diagnostics trace classification's advantage to sharper and more precise separation of return deciles.