This paper identifies nine factors out of a large set of anomalies and macroeconomic factors for explaining hedge fund returns by using machine learning methods. The new factor model outperforms existing models both in sample and out-of-sample. Moreover, the model leads to a significant reduction in hedge fund alphas compared with other models, while revealing substantial cross-sectional performance heterogeneity.
Further subsample analysis provides evidence of style shifting in the hedge fund industry. Overall, the proposed factors quantify well strategies and risk exposures of hedge funds and can be
used for fund performance evaluation.
Download the report to learn more.