Episode 316 - Andrew Chen: "Is everything I was taught about cross-sectional asset pricing wrong?!"
The Rational Reminder Podcast
Machine Learning in Asset Pricing
This chapter explores the evolution of machine learning in asset pricing research, highlighting its transition from a controversial method to a valuable tool for identifying market anomalies. It discusses the balance between data-driven insights and theoretical foundations, emphasizing the importance of rigorous verification in an era of efficient markets.
Are you curious about the hidden factors driving your investment decisions? Today’s guest is Andrew Chen, a Principal Economist at the Federal Reserve Board who focuses on monetary policy and financial stability. Published in leading journals, his research informs key policy decisions and helps shape the Federal Reserve’s strategy for managing economic challenges effectively. In this episode, Andrew delves into the intricacies of meta-research and asset pricing, focusing on cross-sectional asset pricing predictors, replication, and out-of-sample performance in factor investing. We discuss the significance of open-source data and transparency, highlighting Andrew's creation of the Open Source Asset Pricing project, an indispensable and comprehensive dataset for asset pricing predictors. We also address the challenges of replicating financial studies, publication bias, data mining, and false discovery rates, with Andrew offering practical insights on how these factors impact financial research and investment decisions. For actionable insights that could refine your investment strategies and enhance your understanding of financial research, don’t miss this fascinating conversation!
Key Points From This Episode:
(0:03:43) What an asset pricing factor is and how it differs from a predictor.
(0:04:25) Three plausible explanations for why cross-sectional predictors exist.
(0:05:45) Insight into Andrew’s Open Source Asset Pricing project and why it’s so important.
(0:09:49) Where the results of his research diverge from other papers on the subject.
(0:11:42) How the returns on anomalies in his data sample change post-publication.
(0:12:33) Implications of this research for the “replication crisis” in cross-sectional asset pricing.
(0:14:14) Challenges of false discovery rates, publication bias, and out-of-sample returns.
(0:18:37) The effect of transaction costs on expected returns from factor investing.
(0:22:02) Problems with estimating factor expected returns using historical data.
(0:26:08) A big-picture view of the factors with the strongest investable expected returns.
(0:29:12) The relative value of peer-reviewed factors with strong theoretical underpinnings.
(0:35:13) Whether or not machine learning can be useful for asset pricing research.
(0:37:39) Practical advice for using financial research to inform your investment decisions.
(0:40:08) Andrew’s take on the current state of cross-sectional asset pricing.
(0:42:58) The simple way that Andrew defines success for himself.
Links From Today’s Episode:
Rational Reminder on Apple Podcasts — https://podcasts.apple.com/ca/podcast/the-rational-reminder-podcast/id1426530582 Rational Reminder Website — https://rationalreminder.ca/
Rational Reminder on Instagram — https://www.instagram.com/rationalreminder/
Rational Reminder on X — https://x.com/RationalRemind
Rational Reminder on YouTube — https://www.youtube.com/@rationalreminder/
Rational Reminder Email — info@rationalreminder.caBenjamin Felix — https://www.pwlcapital.com/author/benjamin-felix/
Benjamin on X — https://x.com/benjaminwfelix
Benjamin on LinkedIn — https://www.linkedin.com/in/benjaminwfelix/
Cameron Passmore — https://www.pwlcapital.com/profile/cameron-passmore/
Cameron on X — https://x.com/CameronPassmore
Cameron on LinkedIn — https://www.linkedin.com/in/cameronpassmore/
Mark McGrath on LinkedIn — https://www.linkedin.com/in/markmcgrathcfp/ Mark McGrath on X — https://x.com/MarkMcGrathCFP
Andrew Chen — https://sites.google.com/site/chenandrewy/
Federal Reserve Board — https://www.federalreserve.gov/
Andrew Chen on LinkedIn — https://www.linkedin.com/in/andrew-chen-63394169/
Andrew Chen on X — https://x.com/achenfinance
Open Source Asset Pricing Project — https://www.openassetpricing.com/
Center for Research in Security Prices — https://www.crsp.org/
Books From Today’s Episode:
The Adaptive Markets Hypothesis: An Evolutionary Approach to Understanding Financial System Dynamics — https://www.amazon.com/dp/0199681147
Papers From Today’s Episode:
Andrew Chen, Tom Zimmermann, ’Open Source Cross-Sectional Asset Pricing’— https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3604626
Kewei Hou, Chen Xue, Lu Zhang, ’Replicating Anomalies’ — https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3275496
R. David McLean, Jeffrey Pontiff, ’Does Academic Research Destroy Stock Return Predictability?’ — https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2156623
Ilia D. Dichev, ’Is the Risk of Bankruptcy a Systematic Risk?’ — https://papers.ssrn.com/sol3/papers.cfm?abstract_id=99868
Campbell R. Harvey, Yan Liu, Caroline Zhu, ‘…and the Cross-Section of Expected Returns’ — https://papers.ssrn.com/sol3/papers.cfm?abstract_id=2249314
Andrew Chen, Mihail Velikov, ‘Zeroing in on the Expected Returns of Anomalies’ — https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3073681
Andrew Chen, Alejandro Lopez-Lira, Tom Zimmermann, ‘Does Peer-Reviewed Research Help Predict Stock Returns?’ — https://papers.ssrn.com/sol3/papers.cfm?abstract_id=4308069
The AI-powered Podcast Player
