dc.contributor.author | Khandani, Amir Ehsan | |
dc.contributor.author | Kim, Adlar J. | |
dc.contributor.author | Lo, Andrew W. | |
dc.date.accessioned | 2011-10-17T19:26:15Z | |
dc.date.available | 2011-10-17T19:26:15Z | |
dc.date.issued | 2010-06 | |
dc.date.submitted | 2010-05 | |
dc.identifier.issn | 0378-4266 | |
dc.identifier.uri | http://hdl.handle.net/1721.1/66301 | |
dc.description.abstract | We 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.sponsorship | Massachusetts Institute of Technology. Laboratory for Financial Engineering | en_US |
dc.description.sponsorship | Massachusetts Institute of Technology. Center for Future Banking | en_US |
dc.language.iso | en_US | |
dc.publisher | Elsevier B.V. | en_US |
dc.relation.isversionof | http://dx.doi.org/10.1016/j.jbankfin.2010.06.001 | en_US |
dc.rights | Creative Commons Attribution-Noncommercial-Share Alike 3.0 | en_US |
dc.rights.uri | http://creativecommons.org/licenses/by-nc-sa/3.0/ | en_US |
dc.source | Lo | en_US |
dc.title | Consumer Credit-Risk Models Via Machine-Learning Algorithms | en_US |
dc.type | Article | en_US |
dc.identifier.citation | Khandani, 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.department | Massachusetts Institute of Technology. Computer Science and Artificial Intelligence Laboratory | en_US |
dc.contributor.department | Sloan School of Management | en_US |
dc.contributor.department | Sloan School of Management. Laboratory for Financial Engineering | en_US |
dc.contributor.approver | Lo, Andrew W. | |
dc.contributor.mitauthor | Lo, Andrew W. | |
dc.contributor.mitauthor | Khandani, Amir Ehsan | |
dc.contributor.mitauthor | Kim, Adlar J. | |
dc.relation.journal | Journal of Banking and Finance | en_US |
dc.eprint.version | Author's final manuscript | en_US |
dc.type.uri | http://purl.org/eprint/type/JournalArticle | en_US |
eprint.status | http://purl.org/eprint/status/PeerReviewed | en_US |
dspace.orderedauthors | Khandani, Amir E.; Kim, Adlar J.; Lo, Andrew W. | en |
dc.identifier.orcid | https://orcid.org/0000-0003-4909-4565 | |
dc.identifier.orcid | https://orcid.org/0000-0003-2944-7773 | |
mit.license | OPEN_ACCESS_POLICY | en_US |
mit.metadata.status | Complete | |