Key points are not available for this paper at this time.
Credit risk is the critical problem faced by banking and financial sectors when the borrower fails to complete their commitments to pay back. The factors that could increase credit risk are non-performing assets and frauds which are improved by continuous monitoring of payments and other assessment patterns. In past years, few statistical and manual auditing methods were investigated which were not much suitable for tremendous amount of data. Thus, the growth of Artificial Intelligence (AI) with efficient access to big data is focused. However, the effective Deep Learning (DL) and Machine Learning (ML) techniques are introduced to improve the performance and issues in banking and finance sectors by concentrating the business process and customer interaction. In this review, it mainly focusses on the different learning methods-based research articles available in recent years. This review also considers 93 recent research articles that were available in the last 5 years related to the topic of credit risk with different learning methods to tackle traditional challenges. Thus, these advances can make the banking process as smart and fast while preserving themselves from credit defaulters.
Amarnadh et al. (Fri,) studied this question.