Default Risk Modelling in Credit Cards – A Study of Merchant and Acquiring Bank Relationship

Abstract

A globally integrated business environment presents a host of expansion opportunities to the banks, particularly related to credit cards business. These opportunities, however, have risk attached to them. This risk is present in all possible forms: operational risk, financial risk, country risk, etc. Financial risk has a unique nature of being ‘invisible’ at a given point in time. It usually occurs in the future. Hence, it becomes necessary to foresee and predict it. Moreover, in credit cards’ business, financial risk is inherent in the core operations. Banks, in the credit card business, face financial risk in the form of both credit risk and fraud risk. Both of these can be caused by either the card holders or the merchants. In this paper, we have focused on a very specific aspect of the financial risk, known as the credit default risk, posed by the merchants to their respective acquiring banks. We have created a data-driven solution, which explains the relationship between the merchants and their acquiring banks from a credit risk perspective and acts as an “early warning” system for the management. Our solution is based on a logistic regression model, developed using a statistical package called Statistical Analysis System (SAS) This model assesses the merchant portfolio of the acquiring bank and assigns a “probability score” of default (PD) to each merchant. Such a score warns the management in advance of probable future losses on merchant accounts. Banks can rank order merchants based on their PD score, and instead of working on the entire merchant portfolio, they can focus on the relatively riskier set of merchants.