The Anatomy of Machine Learning-Based Portfolio Performance
57 Pages Posted: 29 Nov 2023 Last revised: 7 Dec 2023
Date Written: December 5, 2023
The relevance of asset return predictability is routinely assessed by the economic value that it produces in asset allocation exercises. Specifically, out-of-sample return forecasts are generated based on a set of predictors, increasingly via “black box” machine learning models. The return forecasts then serve as inputs for constructing a portfolio, and portfolio performance metrics are computed over the forecast evaluation period. To shed light on the sources of the economic value generated by return predictability in fitted machine learning models, we develop a methodology based on Shapley values—the Shapley-based portfolio performance contribution (SPPC)—to directly estimate the contributions of individual or groups of predictors to portfolio performance. We illustrate the use of the SPPC in an empirical application measuring the economic value of cross-sectional stock return predictability based on a large number of firm characteristics and machine learning.
Keywords: Asset return predictability, Machine learning, Out-of-sample forecast, Portfolio construction, Economic value, Shapley value, XGBoost
JEL Classification: C53, C55, C58, G11, G17
Suggested Citation: Suggested Citation