Overview and details of the sessions of this conference. Please select a date or location to show only sessions at that day or location. Please select a single session for detailed view (with abstracts and downloads if available).
Please note that all times are shown in the time zone of the conference. The current conference time is: 22nd Dec 2024, 11:02:07am CET
1Federal Reserve Board; 2George Washington University
Discussant: Julio Crego (Tilburg University)
We use empirical Bayes (EB) to mine for out-of-sample returns among 73,108 long-short strategies constructed from accounting ratios, past returns, and ticker symbols. EB predicts returns are concentrated in accounting and past return strategies, small stocks, and pre-2004 samples. The cross-section of out-of-sample return lines up closely with EB predictions. Data-mined portfolios have mean returns comparable with published portfolios, but the data-mined returns are arguably free of data mining bias. In contrast, controlling for multiple testing following Harvey, Liu, and Zhu (2016) misses the vast majority of returns. This "high-throughput asset pricing" provides an evidence-based solution for data mining bias.
The Anatomy of Machine Learning-Based Portfolio Performance
Philippe Goulet Coulombe1, David E. Rapach2, Christian Montes Schutte3, Sander Schwenk-Nebbe4
1Universit´e du Quebec a Montreal; 2Federal Reserve Bank of Atlanta; 3Aarhus University; 4Aarhus University
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.
