Students: Dissertation: Olgay Cangur
ABSTRACT
The current financial environment presents significant challenges for the mortgage industry. Declining house prices have surfaced the importance of delinquency, loan default and loss predictions. Simple models of prepayment behavior are no longer applicable. Investors, originators, servicers and regulators are in need of accurate predictions for their portfolio of interest.
This dissertation focused on two topics relevant to modeling residential mortgages. The first topic provided a framework for modeling delinquencies, prepayments, defaults and losses that represents an enhancement over previous studies. A total of nine loan payment statuses were used (current, thirty days late, sixty days late, ninety days late, early foreclosure, late foreclosure, real estate owned, paid off, and terminated with loss). This framework was compared to the previous framework discussed in the literature that used seven statuses.
The second topic applied reconstructability analysis (RA) to residential mortgage data in order to find new and interesting models. Many statistical methods are unable to reflect non-linearities and significant high-level interactions. RA is capable of doing both. The study explored the hypothesis that the inclusion of RA-suggested interaction terms would improve the accuracy of the logistic regression (LR) models used to forecast loan status changes within mortgage portfolios.
The first topic’s result made two unique and important contributions to the mortgage management literature. First, it determined that nine-state framework yields more accurate results compared to the seven-state framework. It also introduced a new state ‘terminated with loss’ that enabled the framework to predict losses. The second topic’s results confirmed the hypothesis that RA suggested interaction terms improve the performance of LR model. This is a useful contribution to the data mining literature since it enhances the performance of LR which is a widely used data mining methodology.
April 24, 2009
DISSERTATION COMMITTEE
Wayne W. Wakeland, Chair
Martin Zwick
Jong Sung Kim
Beverly Fuller
Tim Anderson, Graduate Studies Rep.
