Financial credit risk evaluation model using machine learning-based approach
by Pankaj Kumar Jadwal; Sonal Jain; Basant Agarwal
World Review of Entrepreneurship, Management and Sustainable Development (WREMSD), Vol. 16, No. 6, 2020

Abstract: Credit risk associated with individual at the time of sanctioning credit is one of the most crucial tasks for the banks and financial institutions. Financial organisations use credit score of a customer to decide whether a loan should be granted or it should be declined. Most of the existing machine learning models are trained to compute the credit risk associated with a person. However, the performance of the existing models is limited due to the noisy nature of available training data. Therefore, the pre-processing of the data contributes a crucial role in the performance of the credit risk evaluation model. In this paper, we propose an approach to develop an efficient credit risk evaluation model based on integrating a clustering algorithm with a classification algorithm. More specifically, initially, we transform the data into clusters of similar nature, and further, we develop different classification models for each cluster. Experimental results show that the proposed model improves the performance of the model by reducing the effect of the noise.

Online publication date: Wed, 25-Nov-2020

The full text of this article is only available to individual subscribers or to users at subscribing institutions.

Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.

Pay per view:
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.

Complimentary Subscribers, Editors or Members of the Editorial Board of the World Review of Entrepreneurship, Management and Sustainable Development (WREMSD):
Login with your Inderscience username and password:

    Username:        Password:         

Forgotten your password?

Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.

If you still need assistance, please email