Machine Learning Versus Economic Restrictions: Evidence from Stock Return Predictability
Open accessThe DOI matches its Crossref record; 103 of the 103 references it cites were found in a registry or an index.
Abstract
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 · cited 1×
“The 𝛽𝑖,𝑡 is estimated in a three-year rolling window with at least 52 weeks of returns prior to the formation period, following Fama and MacBeth (1973).”
BackgroundA 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 105
“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
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Machine Learning Versus Economic Restrictions: Evidence from Stock Return Predictability. https://app.cochat.ai/papers/10.2139/ssrn.3450322
- The paper
- Avramov, D., Cheng, S., & Metzker, L. (2019). Machine Learning Versus Economic Restrictions: Evidence from Stock Return Predictability. SSRN Electronic Journal. https://doi.org/10.2139/ssrn.3450322
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.