{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T19:47:36Z","timestamp":1792007256510,"version":"4.4.0"},"posted":{"date-parts":[[2023]]},"group-title":"SSRN","reference-count":52,"publisher":"Elsevier BV","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>&lt;p&gt;Asset return predictability is routinely assessed by economic value: based on a set of predictors, out-of-sample return forecasts are generated\u2014increasingly via \u201cblack box\u201d machine learning models\u2014which serve as inputs for portfolio construction, and performance metrics are computed over an evaluation period. We develop a flexible methodology based on Shapley values\u2014the &lt;i&gt;Shapley-based portfolio performance contribution&lt;\/i&gt; (SPPC)\u2014to exactly allocate the contributions of individual or groups of predictors to a performance metric. We illustrate the SPPC in an empirical application measuring the economic value of cross-sectional stock return predictability using a large number of firm characteristics and machine learning.&lt;\/p&gt;<\/jats:p>","DOI":"10.2139\/ssrn.4628462","type":"posted-content","created":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T14:53:05Z","timestamp":1701269585000},"source":"Crossref","is-referenced-by-count":1,"title":["The Anatomy of Machine Learning-Based Portfolio Performance"],"prefix":"10.2139","author":[{"given":"Philippe","family":"Goulet Coulombe","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"David","family":"Rapach","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7662-9460","authenticated-orcid":true,"given":"Erik Christian Montes","family":"Sch\u00fctte","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sander","family":"Schwenk-Nebbe","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"ref1","first-page":"2623","article-title":"Optuna: A Next-Generation Hyperparameter Optimization Framework","author":"T Akiba","year":"2019","journal-title":"Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"},{"key":"ref2","article-title":"Intraday Market Return Predictability Culled from the Factor Zoo","author":"S Aleti","year":"2026","journal-title":"Management Science"},{"issue":"4","key":"ref3","doi-asserted-by":"crossref","first-page":"1059","DOI":"10.1111\/rssb.12377","article-title":"Visualizing the Effects of Predictor Variables in Black Box Supervised Learning Models","volume":"82","author":"D W Apley","year":"2020","journal-title":"Journal of the Royal Statistical Society. Series B (Statistical Methodology)"},{"issue":"5","key":"ref4","doi-asserted-by":"crossref","first-page":"2587","DOI":"10.1287\/mnsc.2022.4449","article-title":"Machine Learning Versus Economic Restrictions: Evidence from Stock Return Predictability","volume":"69","author":"D Avramov","year":"2023","journal-title":"Management Science"},{"key":"ref5","article-title":"Arcing the Edge","author":"L Breiman","year":"1997","journal-title":"Statistics Department"},{"issue":"1","key":"ref6","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","article-title":"Random Forests","volume":"45","author":"L Breiman","year":"2001","journal-title":"Machine Learning"},{"key":"ref7","author":"L Breiman","year":"1984","journal-title":"Classification and Regression Trees"},{"issue":"4","key":"ref8","doi-asserted-by":"crossref","first-page":"1509","DOI":"10.1093\/rfs\/hhm055","article-title":"Predicting Excess Stock Returns Out of Sample: Can Anything Beat the Historical Average?","volume":"21","author":"J Y Campbell","year":"2008","journal-title":"Review of Financial Studies"},{"issue":"5","key":"ref9","doi-asserted-by":"crossref","first-page":"1726","DOI":"10.1016\/j.cor.2008.04.004","article-title":"Polynomial Calculation of the Shapley Value Based on Sampling","volume":"36","author":"J Castro","year":"2009","journal-title":"Computer and Operations Research"},{"issue":"2","key":"ref10","doi-asserted-by":"crossref","first-page":"207","DOI":"10.1561\/104.00000112","article-title":"Open Source Cross-Sectional Asset Pricing","volume":"27","author":"A Y Chen","year":"2022","journal-title":"Critical Finance Review"},{"issue":"1","key":"ref11","doi-asserted-by":"crossref","first-page":"590","DOI":"10.1038\/s42256-023-00657-x","article-title":"Algorithms to Estimate Shapley Value Feature Attributions","volume":"5","author":"H Chen","year":"2023","journal-title":"Nature Machine Intelligence"},{"key":"ref12","author":"H Chen","year":"2020"},{"issue":"2","key":"ref13","doi-asserted-by":"crossref","first-page":"714","DOI":"10.1287\/mnsc.2023.4695","article-title":"Deep Learning in Asset Pricing","volume":"70","author":"L Chen","year":"2024","journal-title":"Management Science"},{"key":"ref14","first-page":"785","article-title":"XGBoost: A Scalable Tree Boosting System","author":"T Chen","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"},{"key":"ref15","author":"L W Cong","year":"2022","journal-title":"AlphaPortfolio: Direct Construction Through Deep Reinforcement Learning and Interpretable AI"},{"key":"ref16","first-page":"17212","article-title":"Understanding Global Feature Contributions With Additive Importance Measures","author":"I C Covert","year":"2020","journal-title":"Proceedings of the 34th International Conference on Neural Information Processing Systems"},{"key":"ref17","doi-asserted-by":"crossref","first-page":"598","DOI":"10.1109\/SP.2016.42","article-title":"Algorithmic Transparency via Quantitative Input Influence: Theory and Experiments with Learning Systems","author":"A Datta","year":"2016","journal-title":"2016 IEEE Symposium on Security and Privacy"},{"issue":"1","key":"ref18","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/BF02309007","article-title":"Use of Some Sensitivity Criteria for Choosing Networks with Good Generalization Ability","volume":"2","author":"Y Dimopoulos","year":"1995","journal-title":"Neural Processing Letters"},{"issue":"1","key":"ref19","doi-asserted-by":"crossref","first-page":"23","DOI":"10.1016\/0304-405X(89)90095-0","article-title":"Business Conditions and Expected Returns on Stocks and Bonds","volume":"25","author":"E F Fama","year":"1989","journal-title":"Journal of Financial Economics"},{"issue":"1","key":"ref20","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1016\/j.jfineco.2014.10.010","article-title":"A Five-Factor Asset Pricing Model","volume":"116","author":"E F Fama","year":"2015","journal-title":"Journal of Financial Economics"},{"issue":"2","key":"ref21","doi-asserted-by":"crossref","first-page":"234","DOI":"10.1016\/j.jfineco.2018.02.012","article-title":"Choosing Factors","volume":"128","author":"E F Fama","year":"2018","journal-title":"Journal of Financial Economics"},{"issue":"3","key":"ref22","doi-asserted-by":"crossref","first-page":"607","DOI":"10.1086\/260061","article-title":"Risk, Return, and Equilibrium: Empirical Tests","volume":"81","author":"E F Fama","year":"1973","journal-title":"Journal of Political Economy"},{"key":"ref23","first-page":"1","article-title":"But Many Are Useful: Learning a Variable's Importance by Studying an Entire Class of Prediction Models Simultaneously","volume":"20","author":"A Fisher","year":"2019","journal-title":"Journal of Machine Learning Research"},{"issue":"5","key":"ref24","doi-asserted-by":"crossref","first-page":"2326","DOI":"10.1093\/rfs\/hhz123","article-title":"Dissecting Characteristics Nonparametrically","volume":"33","author":"J Freyberger","year":"2020","journal-title":"Review of Financial Studies"},{"key":"ref25","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy Function Approximation: A Gradient Boosting Machine","volume":"29","author":"J H Friedman","year":"2001","journal-title":"Annals of Statistics"},{"issue":"4","key":"ref26","doi-asserted-by":"crossref","first-page":"367","DOI":"10.1016\/S0167-9473(01)00065-2","article-title":"Stochastic Gradient Boosting","volume":"38","author":"J H Friedman","year":"2002","journal-title":"Computational Statistics & Data Analysis"},{"issue":"1","key":"ref27","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1080\/10618600.2014.907095","article-title":"Peeking Inside the Black Box: Visualizing Statistical Learning with Plots of Individual Conditional Expectation","volume":"24","author":"A Goldstein","year":"2015","journal-title":"Journal of Computational and Graphical Statistics"},{"issue":"12","key":"ref28","doi-asserted-by":"crossref","first-page":"4389","DOI":"10.1093\/rfs\/hhx019","article-title":"The Characteristics that Provide Independent Information about Average U.S. Monthly Stock Returns","volume":"30","author":"J Green","year":"2017","journal-title":"Review of Financial Studies"},{"key":"ref29","author":"B M Greenwell","year":"2018","journal-title":"A Simple and Effective Model-Based Variable Importance Measure"},{"issue":"5","key":"ref30","doi-asserted-by":"crossref","first-page":"2223","DOI":"10.1093\/rfs\/hhaa009","article-title":"Empirical Asset Pricing via Machine Learning","volume":"33","author":"S Gu","year":"2020","journal-title":"Review of Financial Studies"},{"issue":"6","key":"ref31","doi-asserted-by":"crossref","first-page":"1807","DOI":"10.1093\/rof\/rfae027","article-title":"Cross-Sectional Expected Returns: New Fama-MacBeth Regressions in the Era of Machine Learning","volume":"28","author":"Y Han","year":"2024","journal-title":"Review of Finance"},{"issue":"1","key":"ref32","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1093\/rfs\/hhv059","article-title":"and the Cross-Section of Expected Returns","volume":"29","author":"C R Harvey","year":"2016","journal-title":"Review of Financial Studies"},{"key":"ref33","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1093\/rof\/rfaa004","article-title":"An Augmented q-Factor Model with Expected Growth","volume":"25","author":"K Hou","year":"2021","journal-title":"Review of Finance"},{"key":"ref34","first-page":"650","volume":"28","author":"K Hou","year":"2015","journal-title":"Digesting Anomalies: An Investment Approach"},{"key":"ref35","first-page":"2019","volume":"33","author":"K Hou","year":"2020","journal-title":"Replicating Anomalies"},{"key":"ref36","first-page":"2907","article-title":"Feature Relevance Quantification in Explainable AI: A Causal Problem","author":"D Janzing","year":"2020","journal-title":"23rd International Conference on Artificial Intelligence and Statistics"},{"key":"ref37","author":"T I Jensen","year":"2026","journal-title":"Machine Learning and the Implementable Efficient Frontier"},{"issue":"2","key":"ref38","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/j.jfineco.2019.06.008","article-title":"Shrinking the Cross-Section","volume":"135","author":"S Kozak","year":"2020","journal-title":"Journal of Financial Economics"},{"issue":"1","key":"ref39","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1561\/104.00000024","article-title":"The Cross-Section of Expected Stock Returns","volume":"4","author":"J Lewellen","year":"2015","journal-title":"Critical Finance Review"},{"key":"ref40","first-page":"4768","article-title":"A Unified Approach to Interpreting Model Predictions","author":"S M Lundberg","year":"2017","journal-title":"Proceedings of the 31st International Conference on Neural Information Processing Systems"},{"key":"ref41","doi-asserted-by":"crossref","DOI":"10.1016\/j.jfineco.2021.10.006","article-title":"Market Efficiency in the Age of Big Data","volume":"145","author":"I Martin","year":"2022","journal-title":"Journal of Financial Economics"},{"issue":"1","key":"ref42","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1111\/jofi.12365","article-title":"Does Academic Research Destroy Return Predictability","volume":"71","author":"R D Mclean","year":"2016","journal-title":"Journal of Finance"},{"issue":"1","key":"ref43","first-page":"2082","article-title":"Sampling Permutations for Shapley Value Estimation","volume":"23","author":"R Mitchell","year":"2022","journal-title":"Journal of Machine Learning Research"},{"issue":"3","key":"ref44","first-page":"33","article-title":"Portfolio Performance Attribution via Shapley Value","volume":"20","author":"N Moehle","year":"2022","journal-title":"Journal of Investment Management"},{"key":"ref45","author":"C Molnar","year":"2025","journal-title":"Interpretable Machine Learning: A Guide for Making Black Box Models Explainable. CC BY-NC-SA 4.0 License"},{"key":"ref46","author":"S Nagel","year":"2021","journal-title":"Machine Learning in Asset Pricing"},{"key":"ref47","author":"D E Rapach","year":"2022","journal-title":"Asset Pricing: Time-Series Predictability. Oxford Research Encyclopedia of Economics and Finance"},{"key":"ref48","first-page":"1135","article-title":"Explaining the Predictions of Any Classifier","author":"M T Ribeiro","year":"2016","journal-title":"Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining"},{"key":"ref49","first-page":"307","article-title":"A Value for n-Person Games","volume":"2","author":"L S Shapley","year":"1953","journal-title":"Contributions to the Theory of Games"},{"issue":"1","key":"ref50","first-page":"1","article-title":"An Efficient Explanation of Individual Classifications Using Game Theory","volume":"11","author":"E \u0160trumbelj","year":"2010","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"ref51","doi-asserted-by":"crossref","first-page":"647","DOI":"10.1007\/s10115-013-0679-x","article-title":"Explaining Prediction Models and Individual Predictions with Feature Contributions","volume":"41","author":"E \u0160trumbelj","year":"2014","journal-title":"Knowledge and Information Systems"},{"key":"ref52","first-page":"9269","article-title":"The Many Shapley Values for Model Explanation","author":"M Sundararajan","year":"2020","journal-title":"Proceedings of the 37th International Conference on Machine Learning"}],"container-title":[],"original-title":[],"deposited":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T19:05:59Z","timestamp":1792004759000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.ssrn.com\/abstract=4628462"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":52,"URL":"https:\/\/doi.org\/10.2139\/ssrn.4628462","relation":{},"subject":[],"published":{"date-parts":[[2023]]},"subtype":"preprint"}}