Hostname: page-component-6898cfcb55-kwdml Total loading time: 0 Render date: 2026-11-11T21:35:16.584Z Has data issue: false hasContentIssue false
  • English
  • Français

Deep Learning in Characteristics-Sorted Factor Models

Published online by Cambridge University Press:  24 July 2023

Guanhao FengOpen the ORCID record for Guanhao Feng[Opens in a new window],
Jingyu He,
Nicholas G. Polson and
Jianeng Xu
Guanhao Feng
Affiliation:
Department of Management Sciences, City University of Hong Kong gavin.feng@cityu.edu.hk
Jingyu He
Affiliation:
Department of Management Sciences, City University of Hong Kong jingyuhe@cityu.edu.hk
Nicholas G. Polson
Affiliation:
Booth School of Business, University of Chicago ngp@chicagobooth.edu
Jianeng Xu*
Affiliation:
Booth School of Business, University of Chicago
*
jianeng.xu@chicagobooth.edu (corresponding author)
Rights & Permissions [Opens in a new window]

Abstract

Core share and HTML view are not available for this content. However, as you have access to this content, a full PDF is available via the 'Save PDF' action button.

This article presents an augmented deep factor model that generates latent factors for cross-sectional asset pricing. The conventional security sorting on firm characteristics for constructing long–short factor portfolio weights is nonlinear modeling, while factors are treated as inputs in linear models. We provide a structural deep-learning framework to generalize the complete mechanism for fitting cross-sectional returns by firm characteristics through generating risk factors (hidden layers). Our model has an economic-guided objective function that minimizes aggregated realized pricing errors. Empirical results on high-dimensional characteristics demonstrate robust asset pricing performance and strong investment improvements by identifying important raw characteristic sources.

Information

Type
Research Article
Information
Journal of Financial and Quantitative Analysis , Volume 59 , Issue 7 , November 2024, pp. 3001 - 3036
Copyright
© The Author(s), 2023. Published by Cambridge University Press on behalf of the Michael G. Foster School of Business, University of Washington

Footnotes

We appreciate insightful comments from Will Cong, Serge Darolles, Victor DeMiguel, Li Deng, Jin-Chuan Duan, Thierry Foucault (the editor), Shihao Gu (discussant), Bryan Kelly, Soohun Kim (discussant), Markus Pelger (the referee), Weidong Tian (discussant), Dacheng Xiu, and Chu Zhang. We are also grateful to helpful comments from the seminar and conference participants at Boston University, CUHK, CityU HK, Jinan University, SHUFE, SUSTech, ESSEC Business School, 2019 China International Conference in Finance, Bloomberg, 2019 CQAsia Conference, 2019 EcoSta Conference, 2019 Informs Annual Conference, PanAgora Asset Management, 2019 SoFiE Annual Conference, Schroders, 2019 Wolfe Research Conference, 2019 Unigestion Factor Investing Conference, 2019 Autumn Seminar of Inquire Europe, 2018 Australian Finance & Banking Conference, and 2018 New Zealand Finance Meeting. We acknowledge Unigestion Alternative Risk Premia Research Academy, and INQUIRE Europe research awards. Feng’s research is partly supported by HK RGC grants (ECS-21506318 and GRF-11502721) and an NSFC grant (NSFC-72203190). He’s research is partly supported by HK RGC grants (ECS-21504921 and GRF-11507022). Feng and He are partly supported by the InnoHK initiative and the Laboratory for AI-Powered Financial Technologies.

References

Bali, T. G.; Huang, D.; Jiang, F.; and Wen, Q.. “Different Strokes: Return Predictability Across Stocks and Bonds with Machine Learning and Big Data.” Working Paper, Georgetown University (2021).Google Scholar
Bianchi, D.; Büchner, M.; and Tamoni, A.. “Bond Risk Premiums with Machine Learning.” Review of Financial Studies, 34 (2021), 1046–1089.CrossRefGoogle Scholar
Bryzgalova, S.; Huang, J.; and Julliard, C.. “Bayesian Solutions for the Factor Zoo: We Just Ran Two Quadrillion Models.” Journal of Finance, 78 (2023), 487–557.CrossRefGoogle Scholar
Bryzgalova, S.; Pelger, M.; and Zhu, J.. “Forest Through the Trees: Building Cross-Sections of Stock Returns.” Working Paper, London Business School (2020).CrossRefGoogle Scholar
Carhart, M. M. “On Persistence in Mutual Fund Performance.” Journal of Finance, 52 (1997), 57–82.CrossRefGoogle Scholar
Chen, L.; Pelger, M.; and Zhu, J.. “Deep Learning in Asset Pricing.” Management Science, forthcoming (2023).Google Scholar
Chinco, A.; Neuhierl, A.; and Weber, M.. “Estimating the Anomaly Base Rate.” Journal of Financial Economics, 140 (2021), 101–126.CrossRefGoogle Scholar
Cochrane, J. H. “Presidential Address: Discount Rates.” Journal of Finance, 66 (2011), 1047–1108.CrossRefGoogle Scholar
Cong, L. W.; Feng, G.; He, J.; and He, X.. “Asset Pricing with Panel Tree Under Global Split Criteria.” Working Paper, City University of Hong Kong (2022a).CrossRefGoogle Scholar
Cong, L. W.; Feng, G.; He, J.; and Li, J.. “Uncommon Factors for Bayesian Asset Clusters.” Working Paper, City University of Hong Kong (2022b).CrossRefGoogle Scholar
Cong, L. W.; Tang, K.; Wang, J.; and Zhang, Y.. “AlphaPortfolio: Direct Construction Trough Deep Reinforcement Learning and Interpretable AI.” Working Paper, Cornell University (2020).Google Scholar
De Bondt, W. F., and Thaler, R.. “Does the Stock Market Overreact?” Journal of Finance, 40 (1985), 793–805.CrossRefGoogle Scholar
DeMiguel, V.; Martin-Utrera, A.; Nogales, F. J.; and Uppal, R.. “A Transaction-Cost Perspective on the Multitude of Firm Characteristics.” Review of Financial Studies, 33 (2020), 2180–2222.CrossRefGoogle Scholar
Dong, X.; Li, Y.; Rapach, D. E.; and Zhou, G.. “Anomalies and the Expected Market Return.” Journal of Finance, 77 (2022), 639–681.CrossRefGoogle Scholar
Fama, E. F., and French, K. R.. “Common Risk Factors in the Returns on Stocks and Bonds.” Journal of Financial Economics, 33 (1993), 3–56.CrossRefGoogle Scholar
Fama, E. F., and French, K. R.. “A Five-Factor Asset Pricing Model.” Journal of Financial Economics, 116 (2015), 1–22.CrossRefGoogle Scholar
Fan, J.; Ke, Z. T.; Liao, Y.; and Neuhierl, A.. “Structural Deep Learning in Conditional Asset Pricing.” Working Paper, available at https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4117882 (2022a).CrossRefGoogle Scholar
Fan, Y.; Feng, G.; Fulop, A.; and Li, J.. “Real-Time Macro Information and Bond Return Predictability: A Weighted Group Deep Learning Approach.” Working Paper, City University of Hong Kong (2022b).Google Scholar
Feng, G.; Giglio, S.; and Xiu, D.. “Taming the Factor Zoo: A Test of New Factors.” Journal of Finance, 75 (2020), 1327–1370.CrossRefGoogle Scholar
Feng, G., and He, J.. “Factor Investing: A Bayesian Hierarchical Approach.” Journal of Econometrics, 230 (2022), 183–200.CrossRefGoogle Scholar
Feng, G.; Jiang, L.; Li, J.; and Song, Y.. “Deep Tangency Portfolios.” Working Paper, City University of Hong Kong (2022).Google Scholar
Ferson, W. E., and Harvey, C. R.. “Conditioning Variables and the Cross Section of Stock Returns.” Journal of Finance, 54 (1999), 1325–1360.CrossRefGoogle Scholar
Frazzini, A., and Pedersen, L. H.. “Betting Against Beta.” Journal of Financial Economics, 111 (2014), 1–25.CrossRefGoogle Scholar
Freyberger, J.; Neuhierl, A.; and Weber, M.. “Dissecting Characteristics Nonparametrically.” Review of Financial Studies, 33 (2020), 2326–2377.CrossRefGoogle Scholar
Gibbons, M. R.; Ross, S. A.; and Shanken, J.. “A Test of the Efficiency of a Given Portfolio.” Econometrica, (1989), 1121–1152.CrossRefGoogle Scholar
Green, J.; Hand, J. R.; and Zhang, X. F.. “The Characteristics that Provide Independent Information About Average U.S. Monthly Stock Returns.” Review of Financial Studies, 30 (2017), 4389–4436.CrossRefGoogle Scholar
Gu, S.; Kelly, B.; and Xiu, D.. “Empirical Asset Pricing via Machine Learning.” Review of Financial Studies, 33 (2020), 2223–2273.CrossRefGoogle Scholar
Gu, S.; Kelly, B.; and Xiu, D.. “Autoencoder Asset Pricing Models.” Journal of Econometrics, 222 (2021), 429–450.CrossRefGoogle Scholar
Han, Y.; He, A.; Rapach, D.; and Zhou, G.. “What Firm Characteristics Drive US Stock Returns?” Working Paper, Washington University in St. Louis (2018).CrossRefGoogle Scholar
Hansen, L., and Jagannathan, R.. “Implications of Security Market Data for Models of Dynamic Economies.” Journal of Political Economy, 99 (1991), 225–262.CrossRefGoogle Scholar
Harvey, C. R.; Liu, Y.; and Zhu, H.. “… and the Cross-Section of Expected Returns.” Review of Financial Studies, 29 (2016), 5–68.CrossRefGoogle Scholar
He, X.; Feng, G.; Wang, J.; and Wu, C.. “Predicting Individual Corporate Bond Returns.” Working Paper, City University of Hong Kong (2021).CrossRefGoogle Scholar
Heaton, J.; Polson, N.; and Witte, J. H.. “Deep Learning for Finance: Deep Portfolios.” Applied Stochastic Models in Business and Industry, 33 (2017), 3–12.CrossRefGoogle Scholar
Hou, K.; Xue, C.; and Zhang, L.. “Replicating Anomalies.” Review of Financial Studies, 33 (2020), 2019–2133.CrossRefGoogle Scholar
Jegadeesh, N., and Titman, S.. “Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency.” Journal of Finance, 48 (1993), 65–91.CrossRefGoogle Scholar
Jensen, T. I.; Kelly, B. T.; and Pedersen, L. H.. “Is There a Replication Crisis in Finance?” Journal of Finance, 78 (2023), 2465–2518.CrossRefGoogle Scholar
Jiang, J.; Kelly, B. T.; and Xiu, D.. “(Re-) Imag (in) ing Price Trends.” Journal of Finance, forthcoming (2023).CrossRefGoogle Scholar
Kaniel, R.; Lin, Z.; Pelger, M.; and Van Nieuwerburgh, S.. “Machine-Learning the Skill of Mutual Fund Managers.” NBER Working Paper No. 29723 (2022).CrossRefGoogle Scholar
Ke, Z. T.; Kelly, B. T.; and Xiu, D.. “Predicting Returns with Text Data.” NBER Working Paper No. 26186 (2019).CrossRefGoogle Scholar
Kelly, B. T.; Palhares, D.; and Pruitt, S.. “Modeling Corporate Bond Returns.” Journal of Finance, 78 (2023), 1967–2008.CrossRefGoogle Scholar
Kelly, B. T.; Pruitt, S.; and Su, Y.. “Characteristics are Covariances: A Unified Model of Risk and Return.” Journal of Financial Economics, 134 (2019), 501–524.CrossRefGoogle Scholar
Kim, S.; Korajczyk, R. A.; and Neuhierl, A.. “Arbitrage Portfolios.” Review of Financial Studies, 34 (2021), 2813–2856.CrossRefGoogle Scholar
Kozak, S.; Nagel, S.; and Santosh, S.. “Interpreting Factor Models.” Journal of Finance, 73 (2018), 1183–1223.CrossRefGoogle Scholar
Kozak, S.; Nagel, S.; and Santosh, S.. “Shrinking the Cross-Section.” Journal of Financial Economics, 135 (2020), 271–292.CrossRefGoogle Scholar
Lettau, M., and Pelger, M.. “Estimating Latent Asset-Pricing Factors.” Journal of Econometrics, 218 (2020a), 1–31.CrossRefGoogle Scholar
Lettau, M., and Pelger, M.. “Factors that Fit the Time Series and Cross-Section of Stock Returns.” Review of Financial Studies, 33 (2020b), 2274–2325.CrossRefGoogle Scholar
Lewellen, J.; Nagel, S.; and Shanken, J.. “A Skeptical Appraisal of Asset Pricing Tests.” Journal of Financial Economics, 96 (2010), 175–194.CrossRefGoogle Scholar
Light, N.; Maslov, D.; and Rytchkov, O.. “Aggregation of Information About the Cross Section of Stock Returns: A Latent Variable Approach.” Review of Financial Studies, 30 (2017), 1339–1381.CrossRefGoogle Scholar
Merton, R. C. “An Intertemporal Capital Asset Pricing Model.” Econometrica, (1973), 867–887.CrossRefGoogle Scholar
Moskowitz, T. J., and Grinblatt, M.. “Do Industries Explain Momentum?” Journal of Finance, 54 (1999), 1249–1290.CrossRefGoogle Scholar
Novy-Marx, R., and Velikov, M.. “Betting Against Betting Against Beta.” Journal of Financial Economics, 143 (2022), 80–106.CrossRefGoogle Scholar