The DOI matches its Crossref record; 103 of the 103 references it cites were found in a registry or an index.
Machine Learning Versus Economic Restrictions: Evidence from Stock Return Predictability
Open accessAbstract
This paper shows that investments based on deep learning signals extract profitability from difficult-to-arbitrage stocks and during high limits-to-arbitrage market states. In particular, excluding microcaps, distressed stocks, or episodes of high market volatility considerably attenuates profitability. Machine learning-based performance further deteriorates in the presence of reasonable trading costs due to high turnover and extreme positions in the tangency portfolio implied by the pricing kernel. Despite their opaque nature, machine learning methods successfully identify mispriced stocks consistent with most anomalies. Beyond economic restrictions, deep learning signals are profitable in long positions and recent years, and command low downside risk.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Common risk factors in the returns on stocks and bonds
Fama, E. F., & French, K. R. (1993) · Journal of Financial Economics · doi:10.1016/0304-405x(93)90023-5 · Cited by 25,754 · cited 3×
“8 Fama and French (2008) recognize microcaps as stocks with market cap smaller than the 20th NYSE size percentile.”
BackgroundInfluentialOn Persistence in Mutual Fund Performance
Carhart, M. M. (1997) · The Journal of Finance · doi:10.1111/j.1540-6261.1997.tb03808.x · Cited by 17,283
Newey, W. K., & West, K. D. (1987) · Econometrica · doi:10.2307/1913610 · Cited by 16,936
Risk, Return, and Equilibrium: Empirical Tests
Fama, E. F., & MacBeth, J. D. (1973) · Journal of Political Economy · doi:10.1086/260061 · Cited by 14,258
A Simple, Positive Semi-Definite, Heteroskedasticity and AutocorrelationConsistent Covariance Matrix
Newey, W., & West, K. (1986) · National Bureau of Economic Research · doi:10.3386/t0055 · Cited by 12,278
Illiquidity and stock returns: cross-section and time-series effects
Amihud, Y. (2002) · Journal of Financial Markets · doi:10.1016/s1386-4181(01)00024-6 · Cited by 9,963
A five-factor asset pricing model
Fama, E. F., & French, K. R. (2015) · Journal of Financial Economics · doi:10.1016/j.jfineco.2014.10.010 · Cited by 7,852
Liquidity Risk and Expected Stock Returns
Pástor, Ľ., & Stambaugh, R. F. (2003) · Journal of Political Economy · doi:10.1086/374184 · Cited by 5,339
Market Liquidity and Funding Liquidity
Brunnermeier, M. K., & Pedersen, L. H. (2009) · Review of Financial Studies · doi:10.1093/rfs/hhn098 · Cited by 4,835
A comprehensive look at the empirical performance of equity premium prediction
Welch, I., & Goyal, A. (2008) · Review of Financial Studies · doi:10.1093/rfs/hhm014 · Cited by 3,987 · cited 4×
“monthly macroeconomic predictors as in Welch and Goyal (2008), including dividend price ratio, earnings”
BackgroundMethodInfluential
Research works printed but not linked: 5
- M Baker, 2007, Investor sentiment in the stock market, Journal of Economic Perspectives, 21, 129, 10.1257/jep.21.2.129 · DOI · Paper page
- S P Bandyopadhyay, 2010, The accrual volatility anomaly. Working Paper. Bhandari, L. C. 1988. Debt/equity ratio and expected stock returns: Empirical evidence, Journal of Finance, 43, 507
- J H Cochrane, 2011, Discount rates, 66, 1047
- Financial Stability, 2017, Artificial intelligence and machine learning in financial services
- Y Han, 2020, Firm characteristics and expected stock returns
Cited by
Deep Learning in Asset Pricing
Chen, L., Pelger, M., & Zhu, J. (2024) · Management Science · doi:10.1287/mnsc.2023.4695 · Cited by 441
Anomalies and the Expected Market Return
DONG, X., LI, Y., RAPACH, D. E., & ZHOU, G. (2022) · The Journal of Finance · doi:10.1111/jofi.13099 · Cited by 202
Salience Theory and the Cross-Section of Stock Returns: International and Further Evidence
Cakici, N., & Zaremba, A. (2020) · Journal of Financial Economics · doi:10.1016/j.jfineco.2021.10.010 · Cited by 113
Ma, F., Cao, J., Wang, Y., Vigne, S. A., & Dong, D. (2023) · Risk Analysis · doi:10.1111/risa.14265 · Cited by 104
“Understanding the long-term dynamics can provide insights into the sustainability of financial systems and the resilience of ecological assets (see, e.g., Avramov et al., 2023; Evgeniou et al., 2021).”
Does it pay to follow anomalies research? Machine learning approach with international evidence
Tobek, O., & Hronec, M. (2020) · Journal of Financial Markets · doi:10.1016/j.finmar.2020.100588 · Cited by 72
Machine Learning Goes Global: Cross-Sectional Return Predictability in International Stock Markets
Cakici, N., Fieberg, C., Metko, D., & Zaremba, A. (2022) · Journal of Economic Dynamics and Control · doi:10.1016/j.jedc.2023.104725 · Cited by 63
Asset Pricing and Machine Learning: A Critical Review of Empirical Findings
Bagnara, M. (2021) · Journal of Economic Surveys · doi:10.1111/joes.12532 · Cited by 69
AlphaPortfolio for Investment and Economically Interpretable AIPreprint
Cong, L. W., Tang, K., Wang, J., & Zhang, Y. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3554486 · Cited by 58
“Short-term previous return (ret 11 and ret 10) are strongly negatively significant especially for portfolios with large stocks, implying a short-term reversal, which is consistent with Avramov, Cheng, and Metzker (2019).”
BackgroundMethodResultInfluentialEnhancing stock market anomalies with machine learning
Azevedo, V., & Hoegner, C. (2022) · Review of Quantitative Finance and Accounting · doi:10.1007/s11156-022-01099-z · Cited by 52
Machine Learning for Active Portfolio Management
Bartram, S. M., Branke, J., Rossi, G. D., & Motahari, M. (2021) · The Journal of Financial Data Science · doi:10.3905/jfds.2021.1.071 · Cited by 60
Stock picking with machine learning
Wolff, D., & Echterling, F. (2023) · Journal of Forecasting · doi:10.1002/for.3021 · Cited by 48
The Promises and Pitfalls of Machine Learning for Predicting Stock Returns
Leung, E., Lohre, H., Mischlich, D., Shea, Y., & Stroh, M. (2021) · The Journal of Financial Data Science · doi:10.3905/jfds.2021.1.062 · Cited by 33
A Review on Machine Learning for Asset Management
Ferrer, P. M. M., García-García, A., Baixauli‐Soler, J. S., & Prats, M. A. (2022) · Risks · doi:10.3390/risks10040084 · Cited by 43
Deep Sequence Modeling: Development and Applications in Asset Pricing
Cong, L. W., Tang, K., Wang, J., & Zhang, Y. (2020) · The Journal of Financial Data Science · doi:10.3905/jfds.2020.1.053 · Cited by 35
How Many Firm Characteristics Drive US Stock Returns?Preprint
Han, Y., He, A., Rapach, D. E., & Zhou, G. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3185335 · Cited by 25
Maximizing the Sharpe Ratio: A Genetic Programming ApproachPreprint
Yang, L., Zhou, G., & Zhu, Y. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3726609 · Cited by 26
Automated stock picking using random forests
Breitung, C. (2023) · Journal of Empirical Finance · doi:10.1016/j.jempfin.2023.05.001 · Cited by 47
Artificial Intelligence in Strategizing: Prospects and Challenges
von Krogh, G., Ben‐Menahem, S. M., & Shrestha, Y. R. (2021) · Oxford University Press eBooks · doi:10.1093/oso/9780190090883.003.0035 · Cited by 31
Alpha Go Everywhere: Machine Learning and International Stock ReturnsPreprint
Choi, D., Jiang, W., & Zhang, C. (2019) · SSRN Electronic Journal · doi:10.2139/ssrn.3489679 · Cited by 22
Forecasting earnings and returns: A review of recent advancements
Green, J., & Zhao, W. (2022) · The Journal of Finance and Data Science · doi:10.1016/j.jfds.2022.04.004 · Cited by 21
Fundamental characteristics, machine learning, and stock price crash risk
Jiang, F.-W., Ma, T., & Zhu, F.-F. (2024) · Journal of financial markets · doi:10.1016/j.finmar.2024.100908 · Cited by 16
Beyond Fama-French Factors: Alpha from Short-Term Signals
Blitz, D. C., Hanauer, M. X., Honarvar, I., Huisman, R., & van Vliet, P. (2023) · Financial Analysts Journal · doi:10.1080/0015198x.2023.2173492 · Cited by 27
“We use the Baker and Wurgler (2006) market-level investor sentiment index orthogonalized for six macroeconomic variables as a proxy for time-varying investor sentiment.”
MethodMachine learning vs deep learning in stock market investment: an international evidence
Hao, J., He, F., Ma, F., Zhang, S., & Zhang, X. (2023) · Annals of Operations Research · doi:10.1007/s10479-023-05286-6 · Cited by 26
“AsAvramov et al. (2019) argues, high turnover rates make the performance of machine learning portfolios deteriorate in the presence of transaction costs.”
Predicting individual corporate bond returns
Feng, G., He, X., Wang, Y., & Wu, C. (2024) · Journal of Banking & Finance · doi:10.1016/j.jbankfin.2024.107372 · Cited by 22
Shrinking Factor Dimension: A Reduced-Rank ApproachPreprint
Huang, D., Li, J., & Zhou, G. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3205697 · Cited by 17
The commodity risk premium and neural networksPreprint
Rad, H., Low, R. K. Y., Miffre, J., & Faff, R. W. (2021) · SSRN Electronic Journal · doi:10.1016/j.jempfin.2023.101433 · Cited by 18
Navigating the Factor Zoo Around the World: An Institutional Investor Perspective
Bartram, S. M., Lohre, H., Pope, P. F., & Ranganathan, A. (2019) · Journal of Business Economics · doi:10.1007/s11573-021-01035-y · Cited by 30
Predicting corporate policies using downside risk: A machine learning approach
Avramov, D., Li, M., & Wang, H. (2021) · Journal of Empirical Finance · doi:10.1016/j.jempfin.2021.04.009 · Cited by 14
Self-citationThe Term Structure of Machine Learning Alpha
Blitz, D. C., Hanauer, M. X., Hoogteijling, T., & Howard, C. (2023) · The Journal of Financial Data Science · doi:10.3905/jfds.2023.1.135 · Cited by 13
Comparative Analysis of Machine Learning Algorithm to Forecast Indian Stock Market
Rohatgi, S., Singh, D. K. K., & Jasuja, D. (2021) · International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE) · doi:10.1109/icacite51222.2021.9404642 · Cited by 11
Mundlos, P. (2024) · Management Review Quarterly · doi:10.1007/s11301-024-00409-0 · Cited by 18
“…results of AI in predicting government economic growth and recessions (Wu et al. 2020), in investment decisions by predicting stock returns (Avramov et al. 2019), in early identification of emerging technologies (C. Lee et al. 2018) or in recognizing the strategic direction of…”
Predicting Corporate Bond Illiquidity via Machine Learning
Cabrol, A., Drobetz, W., Otto, T., & Puhan, T. X. (2024) · Financial Analysts Journal · doi:10.1080/0015198x.2024.2350952 · Cited by 17
Neural Networks and Value at Risk in Asset ManagementPreprint
Arimond, A., Borth, D., García-Vega, S., Harjoto, M. A., Hoepner, A. G. F., Klawunn, M., & Weisheit, S. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3591996 · Cited by 9
Machine Learning and Return Predictability Across Firms, Time and PortfoliosPreprint
Yara, F. B. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3696533 · Cited by 8
Empirical Asset Pricing via Ensemble Gaussian Process RegressionPreprint
Filipović, D., & Pasricha, P. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4292028 · Cited by 11
Deep Learning from Implied Volatility SurfacesPreprint
Kelly, B. T., Kuznetsov, B., Malamud, S., & Xu, T. A. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4531181 · Cited by 9
Chun, D., Kang, J.-H., & Kim, J. (2024) · Financial Innovation · doi:10.1186/s40854-024-00648-w · Cited by 13
Does it Pay to Follow Anomalies Research? International EvidencePreprint
Tobek, O., & Hronec, M. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3133993 · Cited by 7
Predicting Individual Corporate Bond ReturnsPreprint
He, X., Feng, G., Wang, J. L., & Wu, C. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3870306 · Cited by 7
Asset Pricing: Cross-section PredictabilityPreprint
Zaffaroni, P., & Zhou, G. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4111428 · Cited by 7
Diverging Roads: Theory-Based vs. Machine Learning-Implied Stock Risk PremiaPreprint
Grammig, J., Hanenberg, C., Schlag, C., & Sönksen, J. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3536835 · Cited by 6
Zhang, R., Ren, X., Gu, F., Stefanidis, A., Sun, R., & Su, J. (2022) · International Conference on Cyber-Enabled Distributed Computing and Knowledge Discovery (CyberC) · doi:10.1109/cyberc55534.2022.00031 · Cited by 5
“Although some significant progress is made, many DML models are still not robust enough as their overall performance can be significantly affected by the accuracy of their prediction [3], [5].”
BackgroundCryptocurrency Return Predictability: A Machine-Learning AnalysisPreprint
Filippou, I., Rapach, D. E., & Thimsen, C. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3914414 · Cited by 12
Intangible Assets Aligned: In Search of Return PredictabilityPreprint
Liao, C., Jiang, F., Jin, F., & Tang, G. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3692106 · Cited by 4
Market Efficiency When Machines Access InformationPreprint
Barbopoulos, L. G., Dai, R., Putniņš, T. J., & Saunders, A. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3783221 · Cited by 7
“Retrieved from http://online.wsj.com. stocks and therefore often fail when trading costs and other frictions are taken into consideration (Avramov et al., 2020).”
BackgroundAsset Pricing with Panel Trees Under Global Split CriteriaPreprint
He, X., Cong, L. W., Feng, G., & He, J. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3949463 · Cited by 9
Asset Pricing with Attention Guided Deep LearningPreprint
Chatigny, P., Goyenko, R. Y., & Zhang, C. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.3971876 · Cited by 4
Accuracy of Explanations of Machine Learning Models for Credit DecisionPreprint
Alonso, A., & Carbó, J. M. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4144780 · Cited by 6
“…2020 whose auto-encoder asset pricing model delivers out-ofsample pricing errors that are far smaller compared to other leading factor models, or Avramov et al. 2021 show that investments based on deep learning signals extract profitability from difficult-to-arbitrage stocks), market risk…”
BackgroundWhy Naive 1/N Diversification is Not so Naive, and How to Beat it?Preprint
Yuan, M., & Zhou, G. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4281138 · Cited by 4
The Anatomy of Machine Learning-Based Portfolio PerformancePreprint
Coulombe, P. G., Rapach, D. E., Schütte, E. C. M., & Schwenk-Nebbe, S. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4628462 · Cited by 12
Economic Fundamentals and Short-Run Exchange Rate Prediction: A Machine-Learning Perspective
Filippou, I., Rapach, D. E., Taylor, M., & Zhou, G. (2026) · Journal of Financial and Quantitative Analysis · doi:10.2139/ssrn.3455713 · Cited by 9
Extrapolation: Price vs. ValuePreprint
Huang, D., Zhang, H., Zhou, G., & Zhu, Y. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3678363 · Cited by 3
“Examples include Avramov, Cheng, and Metzker (2020), Feng, Giglio, and Xiu (2020), Gu, Kelly, and Xiu (2020), Liu, Zhou, and Zhu (2020), Bianchi, Buchner, and Tamoni (2021), etc. 9 The expected return is estimated as E[Ri,t+1|MAi,t,n,n≤ Nt ] = Nt ∑ n=1 β nt MAi,t,n, (12) which is what we call…”
Asset Pricing and Machine Learning: A Critical Review of Empirical FindingsPreprint
Bagnara, M. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3950568 · Cited by 3
Why Naive 1/N Diversification Is Not So Naive, and How to Beat It?Preprint
Yuan, M., & Zhou, G. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3991279 · Cited by 3
Painting the black box white: Interpreting an algorithm-based trading strategy
Possatto, A. B. (2022) · Brazilian Review of Finance · doi:10.12660/rbfin.v20n3.2022.81999 · Cited by 2
Stock Picking with Machine LearningPreprint
Wolff, D., & Echterling, F. (2020) · SSRN Electronic Journal · doi:10.2139/ssrn.3607845 · Cited by 2
“In line with Avramov et al. (2020) we employ batch regularization and L1-regularization in each hidden layer with regularization parameter of 0.0001.”
BackgroundMethodInfluentialByun, S. J., Cho, S., & Kim, D. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4001583 · Cited by 2
Multi-(Horizon) Factor Investing with AIPreprint
Goyenko, R. Y., & Zhang, C. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4187056 · Cited by 2
Factor Momentum Versus Stock Price Momentum: A RevisitPreprint
Cakici, N., Fieberg, C., Metko, D., & Zaremba, A. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4454976 · Cited by 2
Construction of a Dynamic Normative Model of the Stock Valuation Rating
Tonkikh, A. S., Tonkikh, S. A., & Maslova, E. Y. (2022) · Finance: Theory and Practice · doi:10.26794/2587-5671-2022-26-3-85-109 · Cited by 1
Customized Stock Return Prediction with Deep Learning
Felder, C., & Mayer, S. (2022) · IEEE Conference on Computational Intelligence for Financial Engineering & Economics · doi:10.1109/cifer52523.2022.9776177 · Cited by 3
Dou, C., Zhao, T., & Guo, Z. (2021) · Advances in economics, business and management research/Advances in Economics, Business and Management Research · doi:10.2991/aebmr.k.210319.139 · Cited by 1
Transfer Learning for Expected ReturnsPreprint
Crego, J. A., Kvaerner, J. S., & Stam, M. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4345646 · Cited by 1
Deep Learning for Conditional Asset Pricing ModelsPreprint
Liu, H. (2021) · SSRN Electronic Journal · doi:10.2139/ssrn.3723237 · Cited by 2
“However, Avramov, Cheng, and Metzker (2020) shows that the machine learning-based return signal is down dramatically after imposing some economic restrictions, such as excluding microcaps.”
BackgroundRise of the Machine-Learning PortfolioPreprint
Sak, H., Huang, T., & Chng, M. T. S. (2018) · SSRN Electronic Journal · doi:10.2139/ssrn.3202277
Forecasting Earnings and Returns: A Review of Recent AdvancementsPreprint
Green, J., & Zhao, W. (2022) · SSRN Electronic Journal · doi:10.2139/ssrn.4095277
The anatomy of out-of-sample forecasting accuracy
Borup, D., Goulet Coulombe, P., Rapach, D. E., Montes Schütte, E. C., & Schwenk-Nebbe, S. (2022) · doi:10.29338/wp2022-16
Guo, Y. (2023) · BCP Business & Management · doi:10.54691/bcpbm.v44i.4910
Essays on Empirical Asset Pricing
Jensen, T. I. (2023) · OpenArchive@CBS (Copenhagen Business School) · doi:10.22439/phd.13.2023
Decomposing Machine-Learning AlphaPreprint
Laurent, A., & Deruaz, A. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4638550
Optimal Portfolio Choice with Economic Constraints: A Genetic Programming ApproachPreprint
Liu, Y., & Zhou, G. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4674858
Dividend Forecasting in the Age of Machine LearningPreprint
Wang, X., Barbopoulos, L. G., & Rzayev, K. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4784398
Lai, S. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5240520 · Cited by 1
Metadata
- Authors
- Avramov, D., Cheng, S., & Metzker, L.
- Affiliations
- Reichman University (IL)
- Syracuse University (US)
- Hebrew University of Jerusalem (IL)
- Corresponding author
- Cheng, Si
- Venue
- SSRN Electronic Journal
- Publisher
- Elsevier BV
- Published
- 2019
- ISSN
- 1556-5068 (ISSN-L)
- OpenAlex
- W2980306936
- Semantic Scholar
- 12b77bed6b71567e61f85723e4458928e56f844c
- Cited by
- 74
- References
- 99
- Citations by year
- 2025: 1 · 2024: 8 · 2023: 14 · 2022: 18 · 2021: 15 · 2020: 12 · 2019: 2
- Type
- posted content
- Language
- en
- Open access
- green
- doi.org
- Locations
- SSRN Electronic Journal (publishedVersion)
- Topics
- Social Sciences › Economics, Econometrics and Finance › Finance › Financial Markets and Investment Strategies
- Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
- Social Sciences › Business, Management and Accounting › Accounting › Financial Analysis and Corporate Governance
- Keywords
- stock return predictability, deep learning, limits to arbitrage, mispricing, trade costs, MicroCAP, market volatility, tangency portfolio, stochastic discount factor, anomalies, downside risk, long-only portfolios
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.