Show simple item record

dc.contributor.authorKhandani, Amir Ehsan
dc.contributor.authorKim, Adlar J.
dc.contributor.authorLo, Andrew W.
dc.date.accessioned2011-10-17T19:26:15Z
dc.date.available2011-10-17T19:26:15Z
dc.date.issued2010-06
dc.date.submitted2010-05
dc.identifier.issn0378-4266
dc.identifier.urihttp://hdl.handle.net/1721.1/66301
dc.description.abstractWe apply machine-learning techniques to construct nonlinear nonparametric forecasting models of consumer credit risk. By combining customer transactions and credit bureau data from January 2005 to April 2009 for a sample of a major commercial bank’s customers, we are able to construct out-of-sample forecasts that significantly improve the classification rates of credit-card-holder delinquencies and defaults, with linear regression R2’s of forecasted/realized delinquencies of 85%. Using conservative assumptions for the costs and benefits of cutting credit lines based on machine-learning forecasts, we estimate the cost savings to range from 6% to 25% of total losses. Moreover, the time-series patterns of estimated delinquency rates from this model over the course of the recent financial crisis suggest that aggregated consumer credit-risk analytics may have important applications in forecasting systemic risk.en_US
dc.description.sponsorshipMassachusetts Institute of Technology. Laboratory for Financial Engineeringen_US
dc.description.sponsorshipMassachusetts Institute of Technology. Center for Future Bankingen_US
dc.language.isoen_US
dc.publisherElsevier B.V.en_US
dc.relation.isversionofhttp://dx.doi.org/10.1016/j.jbankfin.2010.06.001en_US
dc.rightsCreative Commons Attribution-Noncommercial-Share Alike 3.0en_US
dc.rights.urihttp://creativecommons.org/licenses/by-nc-sa/3.0/en_US
dc.sourceLoen_US
dc.titleConsumer Credit-Risk Models Via Machine-Learning Algorithmsen_US
dc.typeArticleen_US
dc.identifier.citationKhandani, Amir E., Adlar J. Kim, and Andrew W. Lo. “Consumer credit-risk models via machine-learning algorithms☆.” Journal of Banking & Finance 34 (2010): 2767-2787.en_US
dc.contributor.departmentMassachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratoryen_US
dc.contributor.departmentSloan School of Managementen_US
dc.contributor.departmentSloan School of Management. Laboratory for Financial Engineeringen_US
dc.contributor.approverLo, Andrew W.
dc.contributor.mitauthorLo, Andrew W.
dc.contributor.mitauthorKhandani, Amir Ehsan
dc.contributor.mitauthorKim, Adlar J.
dc.relation.journalJournal of Banking and Financeen_US
dc.eprint.versionAuthor's final manuscripten_US
dc.type.urihttp://purl.org/eprint/type/JournalArticleen_US
eprint.statushttp://purl.org/eprint/status/PeerRevieweden_US
dspace.orderedauthorsKhandani, Amir E.; Kim, Adlar J.; Lo, Andrew W.en
dc.identifier.orcidhttps://orcid.org/0000-0003-4909-4565
dc.identifier.orcidhttps://orcid.org/0000-0003-2944-7773
mit.licenseOPEN_ACCESS_POLICYen_US


Files in this item

Thumbnail

This item appears in the following Collection(s)

Show simple item record