Application of Linear Logistic and Discriminant Analysis on Forecasting Creditworthiness of Individual Borrowers

Abstract

This research study summarizes the evaluation of credit risk using credit scoring method. Credit scoring is a technique that helps banks decides whether to grant credit to applicants who apply to them or not. The main objective of the research was to evaluate credit risk in commercial banks using credit scoring models by ranking them based on their behavioural financial and non- financial characteristics to honour their debt obligation in future. We applied both logistic regression and discriminant analysis to identify predictors of default and risk factors among cardholders followed for a period of eighteen months. A credit scoring model was developed which can be used by commercial banks to determine the creditworthiness of individual borrowers requesting for credit cards. The results showed out that females constituted 64.3% of the population and they were the most disciplined. Type I and type II errors had been calculated for all the credit scoring models used. The results shows that the proposed model - Linear Logistic Model has more accuracy rate with less misclassification cost errors as compared Discriminant Analysis. Also, several suggestions for further research were presented.