Welcome to the InfoSci Platform
Prediction and Analysis of Financial Crises Using Machine Learning

Prediction and Analysis of Financial Crises Using Machine Learning

S. Baranidharan, Harishchandra Singh Rathod
Copyright: © 2023 |Pages: 15
ISBN13: 9781668483862|ISBN10: 1668483866|ISBN13 Softcover: 9781668483879|EISBN13: 9781668483886
DOI: 10.4018/978-1-6684-8386-2.ch010
Cite Chapter Cite Chapter

MLA

Baranidharan, S., and Harishchandra Singh Rathod. "Prediction and Analysis of Financial Crises Using Machine Learning." Advancement in Business Analytics Tools for Higher Financial Performance, edited by Reza Gharoie Ahangar and Mark Napier, IGI Global, 2023, pp. 200-214. https://doi.org/10.4018/978-1-6684-8386-2.ch010

APA

Baranidharan, S. & Rathod, H. S. (2023). Prediction and Analysis of Financial Crises Using Machine Learning. In R. Gharoie Ahangar & M. Napier (Eds.), Advancement in Business Analytics Tools for Higher Financial Performance (pp. 200-214). IGI Global. https://doi.org/10.4018/978-1-6684-8386-2.ch010

Chicago

Baranidharan, S., and Harishchandra Singh Rathod. "Prediction and Analysis of Financial Crises Using Machine Learning." In Advancement in Business Analytics Tools for Higher Financial Performance, edited by Reza Gharoie Ahangar and Mark Napier, 200-214. Hershey, PA: IGI Global, 2023. https://doi.org/10.4018/978-1-6684-8386-2.ch010

Export Reference

Mendeley
Favorite

Abstract

This study presents a comparative analysis of various machine learning algorithms for credit risk assessment. The algorithms were tested on two credit datasets: German Credit Dataset and Australian Credit Dataset. The performance of the algorithms was evaluated based on several metrics, including sensitivity, specificity, accuracy, F-score, and Kappa. The results showed that the FCPFS-QDNN algorithm outperformed other algorithms in both datasets, achieving high accuracy, sensitivity, specificity, and F-score. On the other hand, the ACO Algorithm and Multilayer Perceptron algorithms were found to perform poorly in both datasets. The findings of this study have significant implications for credit risk assessment in banking and financial institutions. The study recommends the use of the FCPFS-QDNN algorithm for credit risk assessment due to its superior performance compared to other algorithms.

Request Access

You do not own this content. Please login to recommend this title to your institution's librarian or purchase it from the IGI Global bookstore.