A Hybrid Approach of Logistic Regression with Grid Search Optimization in Credit Scoring Modeling for Financial Institutions

With the rapid development of data science and technology, the credit scoring system has changed with many improvements. Building and perfecting a credit scoring system is critical to economic development and economic system reform. On the contrary, the gap of the brand-new personal system facilitates financial institutions like microfinances and banks to perform additional credit functions for various groups of individuals. The purpose of this study was to develop and test an applied credit scoring model that would assist financial institutions in evaluating credit claims. Given the growing importance of credit to our society and concerns about risking it in the wake of the recent financial turmoil, a robust credit rating model will strengthen confidence in the assessments of financial institutions. There is already a stream of literature associated with credit rating. However, this paper emphasizes the need to demonstrate the effectiveness of discriminating between good and bad customers by applying data mining techniques.