Article contents
Machine Learning and the Stock Market
Published online by Cambridge University Press: 11 October 2022
Abstract
Practitioners allocate substantial resources to technical analysis whereas academic theories of market efficiency rule out technical trading profitability. We study this long-standing puzzle by applying a diverse set of machine learning algorithms. The results show that an investor can find profitable technical trading rules using past prices, and that this out-of-sample profitability decreases through time, showing that markets have become more efficient over time. In addition, we find that the evolutionary genetic algorithm’s attitude in not shying away from erroneous predictions gives it an edge in building profitable strategies compared to the strict loss-minimization-focused machine learning algorithms.
- Type
- Research Article
- Information
- Copyright
- © The Author(s), 2022. Published by Cambridge University Press on behalf of the Michael G. Foster School of Business, University of Washington
Footnotes
We thank Deniz Anginer (discussant), Björn Hagströmer, Juhani T. Linnainmaa, Federico Maglione (discussant), Jose Marin, Lars Nordén, Walter Pohl (discussant), Alberto Rossi (the referee), and Pedro Serrano, as well as seminar participants at the Stockholm Business School, 2017 Paris Financial Management Conference, 2018 NFN Young Scholar, 2019 Wolfe Global Quantitative and Macro Investing Conference London, 2020 Paris December Finance Meeting, Man Investments Inc., Menta Capital, and Lynx Asset Management. Zareei is a visiting research fellow at the Swedish House of Finance. He gratefully acknowledges the research funding from the Jan Wallander Foundation, Tom Hedelius Foundation, the Browaldh Foundation, and the Swedish House of Finance.
References
- 16
- Cited by