Date of Award
Doctor of Philosophy in Analytic and Data Science
Statistics and Analytical Sciences
Stefano Mazzotta, PhD
Joe DeMaio, PhD
Jennifer Priestley, PhD
Xiao Huang, PhD
The purpose of this study is to ascertain the statistical and economic significance of non-traditional credit data for individuals who do not have sufficient economic data, collectively known as the unbanked and underbanked. The consequences of not having sufficient economic information often determines whether unbanked and underbanked individuals will receive higher price of credit or be denied entirely. In terms of regulation, there is a strong interest in credit models that will inform policies on how to gradually move sections of the unbanked and underbanked population into the general financial network.
In Chapter 2 of the dissertation, I establish the role of non-traditional credit data, known as alternative data, in modeling borrower default behavior for individuals who unbanked and underbanked individuals by taking a statistical approach. Further, using a combined traditional and alternative auto loan data, I am able to make statements about which alternative data variables contribute to borrower default behavior. Additionally, I devise a way to statistically test the goodness of fit metric for some machine learning classification models to ascertain whether the alternative data truly helps in the credit building process.
In Chapter 3, I discuss the economic significance of incorporating alternative data in the credit modeling process. Using a maximum utility approach, I show that combining alternative and traditional data yields a higher profit for the lender, rather than using either data alone. Additionally, Chapter 3 advocates for the use of loss functions that aligns with a lender's business objective of making a profit.