A Novel Classification Approach for Credit Scoring based on Gaussian Mixture Models

TL;DR

This paper introduces a new credit scoring method using Gaussian Mixture Models that effectively classifies borrowers and is adaptable across different countries, offering a flexible and efficient alternative to traditional techniques.

Contribution

The paper presents a novel Gaussian Mixture Model-based approach for credit scoring that improves classification flexibility and reduces over-fitting without relying on standard cross-validation.

Findings

Model's performance is comparable to existing methods.

The approach avoids over-fitting even without cross-validation.

Effective across datasets from Australia, Japan, and Germany.

Abstract

Credit scoring is a rapidly expanding analytical technique used by banks and other financial institutions. Academic studies on credit scoring provide a range of classification techniques used to differentiate between good and bad borrowers. The main contribution of this paper is to introduce a new method for credit scoring based on Gaussian Mixture Models. Our algorithm classifies consumers into groups which are labeled as positive or negative. Labels are estimated according to the probability associated with each class. We apply our model with real world databases from Australia, Japan, and Germany. Numerical results show that not only our model's performance is comparable to others, but also its flexibility avoids over-fitting even in the absence of standard cross validation techniques. The framework developed by this paper can provide a computationally efficient and powerful tool for assessment of consumer default risk in related financial institutions.