Predicting mortgage default: Lessons from data mining fannie mae mortgage portfolio

Stanislav Mamonov, Raquel Benbunan-Fich

Research output: Chapter in Book/Report/Conference proceedingConference contribution

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.

Original languageEnglish
Title of host publicationProceedings of the International Conferences on ICT, Society, and Human Beings 2016, Web Based Communities and Social Media 2016, Big Data Analytics, Data Mining and Computational Intelligence 2016 and Theory and Practice in Modern Computing 2016 - Part of the Multi Conference on Computer Science and Information Systems 2016
EditorsLuis Rodrigues, Ajith P. Abraham, Jorg Roth, Piet Kommers
PublisherIADIS
Pages187-194
Number of pages8
ISBN (Electronic)9789898533548
StatePublished - 1 Jan 2016
Event2017 International Conferences on Information and Communication Technology, Society, and Human Beings, ICT 2016, Web Based Communities and Social Media, WBC 2016, Big Data Analytics, Data Mining and Computational Intelligence, BIGDACI 2016 and Theory and Practice in Modern Computing, TPMC 2016 - Madeira, Portugal
Duration: 1 Jul 20164 Jul 2016

Publication series

NameProceedings of the International Conferences on ICT, Society, and Human Beings 2016, Web Based Communities and Social Media 2016, Big Data Analytics, Data Mining and Computational Intelligence 2016 and Theory and Practice in Modern Computing 2016 - Part of the Multi Conference on Computer Science and Information Systems 2016

Other

Other2017 International Conferences on Information and Communication Technology, Society, and Human Beings, ICT 2016, Web Based Communities and Social Media, WBC 2016, Big Data Analytics, Data Mining and Computational Intelligence, BIGDACI 2016 and Theory and Practice in Modern Computing, TPMC 2016
CountryPortugal
CityMadeira
Period1/07/164/07/16

Fingerprint

Data mining
Finance
Information technology

Keywords

  • Credit score
  • Data mining
  • Debt-toincome
  • Delinquency
  • Government sponsored enterprises
  • Loan-to-value
  • Mortgage default

Cite this

Mamonov, S., & Benbunan-Fich, R. (2016). Predicting mortgage default: Lessons from data mining fannie mae mortgage portfolio. In L. Rodrigues, A. P. Abraham, J. Roth, & P. Kommers (Eds.), Proceedings of the International Conferences on ICT, Society, and Human Beings 2016, Web Based Communities and Social Media 2016, Big Data Analytics, Data Mining and Computational Intelligence 2016 and Theory and Practice in Modern Computing 2016 - Part of the Multi Conference on Computer Science and Information Systems 2016 (pp. 187-194). (Proceedings of the International Conferences on ICT, Society, and Human Beings 2016, Web Based Communities and Social Media 2016, Big Data Analytics, Data Mining and Computational Intelligence 2016 and Theory and Practice in Modern Computing 2016 - Part of the Multi Conference on Computer Science and Information Systems 2016). IADIS.
Mamonov, Stanislav ; Benbunan-Fich, Raquel. / Predicting mortgage default : Lessons from data mining fannie mae mortgage portfolio. Proceedings of the International Conferences on ICT, Society, and Human Beings 2016, Web Based Communities and Social Media 2016, Big Data Analytics, Data Mining and Computational Intelligence 2016 and Theory and Practice in Modern Computing 2016 - Part of the Multi Conference on Computer Science and Information Systems 2016. editor / Luis Rodrigues ; Ajith P. Abraham ; Jorg Roth ; Piet Kommers. IADIS, 2016. pp. 187-194 (Proceedings of the International Conferences on ICT, Society, and Human Beings 2016, Web Based Communities and Social Media 2016, Big Data Analytics, Data Mining and Computational Intelligence 2016 and Theory and Practice in Modern Computing 2016 - Part of the Multi Conference on Computer Science and Information Systems 2016).
@inproceedings{4aca1c11246c4f52a90ef6d355b64191,
title = "Predicting mortgage default: Lessons from data mining fannie mae mortgage portfolio",
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.",
keywords = "Credit score, Data mining, Debt-toincome, Delinquency, Government sponsored enterprises, Loan-to-value, Mortgage default",
author = "Stanislav Mamonov and Raquel Benbunan-Fich",
year = "2016",
month = "1",
day = "1",
language = "English",
series = "Proceedings of the International Conferences on ICT, Society, and Human Beings 2016, Web Based Communities and Social Media 2016, Big Data Analytics, Data Mining and Computational Intelligence 2016 and Theory and Practice in Modern Computing 2016 - Part of the Multi Conference on Computer Science and Information Systems 2016",
publisher = "IADIS",
pages = "187--194",
editor = "Luis Rodrigues and Abraham, {Ajith P.} and Jorg Roth and Piet Kommers",
booktitle = "Proceedings of the International Conferences on ICT, Society, and Human Beings 2016, Web Based Communities and Social Media 2016, Big Data Analytics, Data Mining and Computational Intelligence 2016 and Theory and Practice in Modern Computing 2016 - Part of the Multi Conference on Computer Science and Information Systems 2016",

}

Mamonov, S & Benbunan-Fich, R 2016, Predicting mortgage default: Lessons from data mining fannie mae mortgage portfolio. in L Rodrigues, AP Abraham, J Roth & P Kommers (eds), Proceedings of the International Conferences on ICT, Society, and Human Beings 2016, Web Based Communities and Social Media 2016, Big Data Analytics, Data Mining and Computational Intelligence 2016 and Theory and Practice in Modern Computing 2016 - Part of the Multi Conference on Computer Science and Information Systems 2016. Proceedings of the International Conferences on ICT, Society, and Human Beings 2016, Web Based Communities and Social Media 2016, Big Data Analytics, Data Mining and Computational Intelligence 2016 and Theory and Practice in Modern Computing 2016 - Part of the Multi Conference on Computer Science and Information Systems 2016, IADIS, pp. 187-194, 2017 International Conferences on Information and Communication Technology, Society, and Human Beings, ICT 2016, Web Based Communities and Social Media, WBC 2016, Big Data Analytics, Data Mining and Computational Intelligence, BIGDACI 2016 and Theory and Practice in Modern Computing, TPMC 2016, Madeira, Portugal, 1/07/16.

Predicting mortgage default : Lessons from data mining fannie mae mortgage portfolio. / Mamonov, Stanislav; Benbunan-Fich, Raquel.

Proceedings of the International Conferences on ICT, Society, and Human Beings 2016, Web Based Communities and Social Media 2016, Big Data Analytics, Data Mining and Computational Intelligence 2016 and Theory and Practice in Modern Computing 2016 - Part of the Multi Conference on Computer Science and Information Systems 2016. ed. / Luis Rodrigues; Ajith P. Abraham; Jorg Roth; Piet Kommers. IADIS, 2016. p. 187-194 (Proceedings of the International Conferences on ICT, Society, and Human Beings 2016, Web Based Communities and Social Media 2016, Big Data Analytics, Data Mining and Computational Intelligence 2016 and Theory and Practice in Modern Computing 2016 - Part of the Multi Conference on Computer Science and Information Systems 2016).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - Predicting mortgage default

T2 - Lessons from data mining fannie mae mortgage portfolio

AU - Mamonov, Stanislav

AU - Benbunan-Fich, Raquel

PY - 2016/1/1

Y1 - 2016/1/1

N2 - 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.

AB - 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.

KW - Credit score

KW - Data mining

KW - Debt-toincome

KW - Delinquency

KW - Government sponsored enterprises

KW - Loan-to-value

KW - Mortgage default

UR - http://www.scopus.com/inward/record.url?scp=85040218289&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:85040218289

T3 - Proceedings of the International Conferences on ICT, Society, and Human Beings 2016, Web Based Communities and Social Media 2016, Big Data Analytics, Data Mining and Computational Intelligence 2016 and Theory and Practice in Modern Computing 2016 - Part of the Multi Conference on Computer Science and Information Systems 2016

SP - 187

EP - 194

BT - Proceedings of the International Conferences on ICT, Society, and Human Beings 2016, Web Based Communities and Social Media 2016, Big Data Analytics, Data Mining and Computational Intelligence 2016 and Theory and Practice in Modern Computing 2016 - Part of the Multi Conference on Computer Science and Information Systems 2016

A2 - Rodrigues, Luis

A2 - Abraham, Ajith P.

A2 - Roth, Jorg

A2 - Kommers, Piet

PB - IADIS

ER -

Mamonov S, Benbunan-Fich R. Predicting mortgage default: Lessons from data mining fannie mae mortgage portfolio. In Rodrigues L, Abraham AP, Roth J, Kommers P, editors, Proceedings of the International Conferences on ICT, Society, and Human Beings 2016, Web Based Communities and Social Media 2016, Big Data Analytics, Data Mining and Computational Intelligence 2016 and Theory and Practice in Modern Computing 2016 - Part of the Multi Conference on Computer Science and Information Systems 2016. IADIS. 2016. p. 187-194. (Proceedings of the International Conferences on ICT, Society, and Human Beings 2016, Web Based Communities and Social Media 2016, Big Data Analytics, Data Mining and Computational Intelligence 2016 and Theory and Practice in Modern Computing 2016 - Part of the Multi Conference on Computer Science and Information Systems 2016).