Intelligent System for Credit Risk Management in Financial Institutions

Review Of Related Works

The application of artificial intelligence and machine learning systems for credit risk management has received extensive academic research in recent years. Credit risk means the probability of non-repayment of bank financial facilities granted to investors (Nazari, 2013; Weber et al., 2015). Credit risk management is defined as identification, measurement, monitoring and control of risk arising from the possibility of default in loan repayments (Kithinji, 2010; Wu et al., 2014). Poor credit risk management or evaluation constitutes the major reason financial institutions become bankrupt due to the huge amount of money being locked up when borrowers defaults. This is the reason why the development of a great variety of strategies to implement reliable prediction models has attracted considerable attention both from academicians and financial analysts over the last decades. Several researchers have explored and analyze the ability machine learning to develop models and software to forecast the credit risk. Alshatti (2015) investigated the impact of credit risk management on bank’s financial performance, through ascertaining the credit risk management and financial performance indicators, and to find a pragmatic proof of the degree to which credit risk management affects banks’ financial performance. Credit scoring has been acknowledged as a two-fold classification technique, distinguishing applicants into two groups: good credit and bad credit, based on features such as gender, age, occupation, and salary. These conclude the applicability of loans for applicants. There are two conventional classification techniques, statistical techniques and machine learning techniques (He et al., 2018).