Machine Learning Classification Methods and Portfolio Allocation: An Examination of Market Efficiency
Fiche du document
4 août 2021
- 2108.02283
Mots-clés
Quantitative Finance - General Finance Computer Science - Machine Learning Economics - General Economics Quantitative Finance - Computational Finance Quantitative Finance - Portfolio ManagementSujets proches
Learning, Machine Funds Funding Finance, commerce, confiscations, etcCiter ce document
Yang Bai et al., « Machine Learning Classification Methods and Portfolio Allocation: An Examination of Market Efficiency », arXiv - économie
Partage / Export
Résumé
We design a novel framework to examine market efficiency through out-of-sample (OOS) predictability. We frame the asset pricing problem as a machine learning classification problem and construct classification models to predict return states. The prediction-based portfolios beat the market with significant OOS economic gains. We measure prediction accuracies directly. For each model, we introduce a novel application of binomial test to test the accuracy of 3.34 million return state predictions. The tests show that our models can extract useful contents from historical information to predict future return states. We provide unique economic insights about OOS predictability and machine learning models.