An unsupervised credit scoring system for unsecured loan lending
Due to growmg competition, over-indebtedness, and economic crises, banks have to pursue their social and financial objectives in an increasingly constrained environment. The key determinant of Survival, competition and profitability is the quality of bank loans they give to their customer. Consequently, developing powerful risk management tools becomes more than ever crucial to survive. Credit scoring has been discussed in this study as one of the most important kits to classify loan applicants as "good" or "bad" The study also discusses how a credit scoring system can be developed to remove redundancies and biases of credit officers in the credit scoring process, mitigate the risk of lender to borrower and reduce the turnaround time of loan application. It discusses the best techniques and key determinants in developing such a systems and factors that should be considered to guarantee the accuracy of the system. A mixed method research design was used to investigate and review the various credit evaluation techniques and to also analyze various credit scoring techniques that may be used to develop the unsupervised credit scoring system. Discriminant analysis was the preferred technique in development of the credit scoring system due to its ease of use and implementation. Literature reviewed also discusses it as one of the most widely used technique. The research findings showed that even though credit scoring tools were in place, the reliance on them was very low. Age, marital status, education and history of the applicant have been discussed as some of the most important factors in developing a credit scoring system.