Predicting stock returns with financial ratios: A new methodology incorporating machine learning techniques to beat the market

Zeynep İltüzer

Asia-Pacific Journal of Accounting & Economics, 2023, vol. 30, issue 3, 619-632

Abstract: This study proposes a methodology incorporating machine learning algorithms to predict stock returns and construct portfolios that beat the market. The performance evaluation is based on the statistical metrics as well as the return and Sharpe ratios of the portfolios. Additionally, a new performance evaluation metric, Safe-Side, is introduced to address the needs of conservative portfolio managers and investors. The results provide strong evidence that the machine learning algorithms can be used to predict the stock returns with approximately 86% classification accuracy. The proposed methodology also provides guidance for investors and portfolio managers for their portfolio selection problems.

Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
http://hdl.handle.net/10.1080/16081625.2021.2007408 (text/html)
Access to full text is restricted to subscribers.

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:taf:raaexx:v:30:y:2023:i:3:p:619-632

Ordering information: This journal article can be ordered from
http://www.tandfonline.com/pricing/journal/raae20

DOI: 10.1080/16081625.2021.2007408

Access Statistics for this article

Asia-Pacific Journal of Accounting & Economics is currently edited by Yin-Wong Cheung, Hong Hwang, Jeong-Bon Kim, Shu-Hsing Li and Suresh Radhakrishnan

More articles in Asia-Pacific Journal of Accounting & Economics from Taylor & Francis Journals
Bibliographic data for series maintained by Chris Longhurst ().