A Comparitive Study of Support Vector Machine and Logistic Regression in Credit Scorecard Model

Abstract

Credit analysts generally assess the risk of credit applications based on their previous experience. They frequently employ quantitative methods to this end. Most of the financial and banking institutions are using logistic regression to build a credit scorecard. Among the new method, Support Vector Machines (SVM) has been applied in various studies of scorecard modelling. SVM classification is currently an active research area and successfully solves classification problems in many domains. This paper uses standard logistic regression models and compares them with the more advanced least squares support vector machine models with linear and radial basis function kernels. A microfinance data set is used to test the model performance.