PERFORMANCE OF USING MACHINE LEARNING APPROACHES FOR CREDIT RATING PREDICTION: RANDOM FOREST AND BOOSTING ALGORITHMS

W. Paul Chiou (), Yuchen Dong () and Sofia Ma ()
Additional contact information
W. Paul Chiou: Northeastern University, Postal: 360 Huntington Ave., Boston, MA 02215, https://damore-mckim.northeastern.edu/people/w-paul-chiou/
Yuchen Dong: MathWorks
Sofia Ma: MathWorks

Journal of Financial Transformation, 2023, vol. 58, 44-53

Abstract: Applying machine learning techniques to improve the accuracy and efficiency of predictions of credit risk rating is increasingly critical to the financial industry. In this study, we apply MATLAB to investigate the performance of two approaches, decision forest and boosting algorithms, by using a wide range of financial data. The empirical outcomes suggest that both methods exhibit considerable performance but may be superior in different scenarios. Boosting algorithms method exhibits accuracy rates of approximately 67% across the credit rating categories. The decision forests model generates lower accuracy rates for low and medium classifications than the boosting method, but the accuracy rate for high credit ratings reaches 79%, more accurate than the outcome using the boosting method.

Keywords: Machine learning; MATLAB (search for similar items in EconPapers)
JEL-codes: G17 (search for similar items in EconPapers)
Date: 2023
References: Add references at CitEc
Citations:

Downloads: (external link)
https://www.capco.com/Capco-Institute/Journal-58-Artificial-Intelligence Full text (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:ris:jofitr:2345

Access Statistics for this article

Journal of Financial Transformation is currently edited by Prof. Shahin Shojai

More articles in Journal of Financial Transformation from Capco Institute 77 Water Street, 10th Floor, New York NY 10005.
Bibliographic data for series maintained by Prof. Shahin Shojai ( this e-mail address is bad, please contact ).