Assessing and Evaluating the Effectiveness of Different Credit Scoring Models using

ROC curve Analysis

[Name of the Institute

Assessing and Evaluating the Effectiveness of Different Credit Scoring Models using

ROC curve Analysis

Introduction

The statistical analysis of rating model is based on the assumptions that for a pre-defined time horizon, there are two groups of bank obligors, those that will be in default, called defaulters, and those that will not be in default, called non defaulters. It is not observable in advance whether an obligator will be a defaulter or a non-defaulter in the next time horizon. Banks have loan books or credit portfolios; they have to assess an obligor's future status based on a set of his or her present observable characterstics. Rating systems may be regarded as classification tools to provide signals and indications of the obligor's possible future status. A rating score is returned for each obligor based on a rating model, usually an Expert Judgment Model. The main principle of rating systems is that “the better a grade, the smaller the proportion of defaulters and the greater the proportion of non defaulters that are assigned this grade”.

Therefore, the quality of rating system is determined by its discriminatory power between non-defaulting obligors and defaulters for a specific time horizon, usually a year. The CAP measure and ROC provide statistical measures to assess the discriminatory power of various rating models based on historical data. The quantitative method known as credit scoring has been developed for the credit assessment problem. Credit scoring is essentially an application of classification techniques, which classify credit customers into different risk groups. Since the classification technique is one of the data mining techniques, the process of credit scoring can be seen as the process of a data mining application. It utilizes new developed data mining techniques to preprocess input data and to build classification models. The popularity of consumer credit products represents both a risk and an opportunity for credit lenders. The credit industry has experienced decades of rapid growth as characterized by the ubiquity of consumer financial products such as credit cards, mortgages, home equity loans, auto loans, interest-only loans, etc. In 1980, there was $55.1 billion in outstanding unsecured revolving consumer credit in the U.S. In 2000, that number had risen to $633.2 billion.

However, the number of bankruptcies filed per 1,000 U.S. Household increased from 1 to 5 over the same period. In an effort to maximize the opportunity to attract, manage, and retain profitable customers and minimize the risks associated with potentially unprofitable customers, lenders have increasingly turned to modeling to facilitate a holistic approach to Customer Relationship Management (CRM). In the consumer credit industry, the general framework for CRM includes product planning, customer acquisition, customer management, collections and recovery. Prediction models have been used extensively to support each stage of this general CRM strategy.

Credit scoring is a complex data mining process. When various innovative data mining techniques are introduced into the process of model building, a large number of classification models (also called classifiers) may ...