Predicting Mortgage Default: Lessons from Data Mining Fannie Mae Mortgage Portfolio
Document Type
Conference Proceeding
Publication Date
1-1-2016
Journal / Book Title
International Journal on Computer Science & Information Systems
Abstract
Recent advances in information technology have made possible the analysis of vast amounts of data. One promising area for the application of the new analytical methods is finance. We perform data mining on the Fannie Mae mortgage portfolio from the fourth quarter of 2007 that includes 341,348 mortgages with the total principal value of more than $70 billion. This portfolio had the highest delinquency rate in the agency's history - 19.4% versus the historical average of 1.7%. We find that although a number of information variables that were available at the time of mortgage acquisition in Q4, 2007 are correlated with the subsequent delinquencies, application of data mining techniques fails to accurately capture the mortgage delinquency patterns in the historical data. These results are consistent with an exogenous shock explanation and reveal a fundamental challenge that can arise in data mining large datasets.
MSU Digital Commons Citation
Mamonov, Stanislav and Benbunan-Fich, Raquel, "Predicting Mortgage Default: Lessons from Data Mining Fannie Mae Mortgage Portfolio" (2016). Department of Information Management and Business Analytics Faculty Scholarship and Creative Works. 103.
https://digitalcommons.montclair.edu/infomgmt-busanalytics-facpubs/103
Published Citation
Mamonov, S., & Benbunan-Fich, R. (2016). PREDICTING MORTGAGE DEFAULT: LESSONS FROM DATA MINING FANNIE MAE MORTGAGE PORTFOLIO. IADIS International Journal on Computer Science & Information Systems, 11(2).