The Fama–French Five-Factor Model with Hurst Exponents Compared with Machine Learning Methods

Yicun Li and Yuanyang Teng ()
Additional contact information
Yicun Li: Business School, Research Center of Digital Transformation and Social Responsibility Management, Hangzhou City University (HZCU), Hangzhou 310015, China
Yuanyang Teng: School of Management, Zhejiang University, Hangzhou 310027, China

Mathematics, 2023, vol. 11, issue 13, 1-19

Abstract: Scholars and investors have been interested in factor models for a long time. This paper builds models using the monthly data of the A-share market. We construct a seven-factor model by adding the Hurst exponent factor and the momentum factor to a Fama–French five-factor model and find that there is a 7% improvement in the average R–squared. Then, we compare five machine learning algorithms with ordinary least squares (OLS) in one representative stock and all A-Share stocks. We find that regularization algorithms, such as lasso and ridge, have worse performance than OLS. SVM and random forests have a good improvement in fitting power, while the neural network is not always better than OLS, depending on the data, frequency, period, etc.

Keywords: Fama–French five-factor model; Hurst exponent; momentum factor; machine learning (search for similar items in EconPapers)
JEL-codes: C (search for similar items in EconPapers)
Date: 2023
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://www.mdpi.com/2227-7390/11/13/2988/pdf (application/pdf)
https://www.mdpi.com/2227-7390/11/13/2988/ (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:gam:jmathe:v:11:y:2023:i:13:p:2988-:d:1186815

Access Statistics for this article

Mathematics is currently edited by Ms. Emma He

More articles in Mathematics from MDPI
Bibliographic data for series maintained by MDPI Indexing Manager ().