Authors: Pankaj Kumar Jadwal; Sonal Jain; Basant Agarwal
Addresses: Department of Computer Science and Engineering, JK Lakshmipat University, Jaipur, India ' Department of Computer Science and Engineering, JK Lakshmipat University, Jaipur, India ' Department of Computer Science and Engineering, Indian Institute of Information Technology Kota, MNIT Campus, Jaipur, India
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.
Keywords: credit risk; clustering; classification; hybrid model; agglomerative clustering; k-mode clustering.
World Review of Entrepreneurship, Management and Sustainable Development, 2020 Vol.16 No.6, pp.576 - 589
Received: 23 Nov 2018
Accepted: 05 Feb 2019
Published online: 25 Nov 2020 *