Use of quantitative methods in temporal decision making problems

Abstract

Certain problems in real life are essentially long time duration problems where the overall transaction happens over a period of time. These set of models can be considered as temporal decision making problems. One example of such a problem is scheduled loan repayment. The lender in such circumstances estimates the potential risk based on profile of the customer based on demographics and issues the loans. However, the loan gets repaid on a long duration of time as a payment schedule. The static models which are purely based on demographics are useful in determining initial credit qualification but this does not have ability to take actionable decision making during the loan time period. We devise a statistical techniques based on panel data models that can aid lenders to take actionable decisions based on the creditors actual payment schedules. In this report we present the kind of research which is popular in the credit rating models available in the public domain.