{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T17:02:39Z","timestamp":1780333359324,"version":"3.54.1"},"reference-count":59,"publisher":"MIS Quarterly","issue":"2","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,6,1]]},"abstract":"<jats:p>Given the sheer size of the consumer credit market and the huge number of consumer credit users, credit risk prediction, or predicting the probability of consumer credit delinquency (or default), has become a critical problem in the consumer credit industry. Effective credit risk prediction aids financial institutions in granting and managing extensions of credit and can help secure the availability of credit for worthy applicants. While it is desirable to employ both users\u2019 intrinsic characteristics and similarities among them for effective credit risk prediction, existing studies rely solely on similarities derived from their observed characteristics and fail to account for unobserved similarities among them. To address this challenge, we propose a latent similarity-enhanced credit risk prediction model, which operationalizes the similarity between a pair of users as a combination of the observed and latent similarities between them. We then present a new design for a new method that estimates the model parameters, learns latent similarities among users, and integrates both observed and latent similarities among users with their intrinsic characteristics for credit risk prediction. We further extend our method to the multiclass and numerical credit risk prediction problems. Extensive empirical evaluations with real-world data demonstrate the superior predictive power of our method over benchmark methods for a broad spectrum of credit risk prediction problems. We also show substantial economic value generated from the superiority of our method through a case study.<\/jats:p>","DOI":"10.25300\/misq\/2025\/18080","type":"journal-article","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T17:33:50Z","timestamp":1761932030000},"page":"731-766","source":"Crossref","is-referenced-by-count":0,"title":["Latent Similarity-Enhanced Credit Risk Prediction"],"prefix":"10.25300","volume":"50","author":[{"given":"Hongzhe","family":"Zhang","sequence":"first","affiliation":[{"name":"Shenzhen Finance Institute, School of Management and Economics, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Qian","sequence":"additional","affiliation":[{"name":"Department of Applied Economics and Statistics, University of Delaware, Newark, DE, U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Fang","sequence":"additional","affiliation":[{"name":"Lerner College of Business and Economics, University of Delaware, Newark, DE, U.S.A."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"10933","published-online":{"date-parts":[[2026,6,1]]},"reference":[{"key":"2026060112023817900_b1-12_ra_10_25300_misq_2025_18080","volume-title":"Recovery risk: The next challenge in credit risk management","author":"Altman","year":"2005"},{"key":"2026060112023817900_b2-12_ra_10_25300_misq_2025_18080","volume-title":"How bad was it? The costs and consequences of the 2007-09 financial crisis","author":"Atkinson","year":"2013"},{"key":"2026060112023817900_b3-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"2183","DOI":"10.1145\/3292500.3330693","article-title":"E.T.-RNN: Applying deep learning to credit loan applications","author":"Babaev","year":"2019"},{"issue":"6","key":"2026060112023817900_b4-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"627","DOI":"10.1057\/palgrave.jors.2601545","article-title":"Benchmarking state-of-the-art classification algorithms for credit scoring","volume":"54","author":"Baesens","year":"2003","journal-title":"Journal of the Operational Research Society"},{"key":"2026060112023817900_b5-12_ra_10_25300_misq_2025_18080","volume-title":"Nonlinear programming","author":"Bertsekas","year":"1999","edition":"2nd"},{"issue":"2","key":"2026060112023817900_b6-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"123","DOI":"10.1007\/BF00058655","article-title":"Bagging predictors","volume":"24","author":"Breiman","year":"1996","journal-title":"Machine Learning"},{"issue":"2","key":"2026060112023817900_b7-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1023\/A:1009715923555","article-title":"A tutorial on support vector machines for pattern recognition","volume":"2","author":"Burges","year":"1998","journal-title":"Data Mining and Knowledge Discovery"},{"issue":"1","key":"2026060112023817900_b8-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"191","DOI":"10.2307\/2347628","article-title":"Ridge estimators in logistic regression","volume":"41","author":"Cessie","year":"1992","journal-title":"Journal of the Royal Statistical Society Series C: Applied Statistics"},{"issue":"6","key":"2026060112023817900_b9-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"1525","DOI":"10.1111\/j.1468-0262.2007.00806.x","article-title":"A quantitative theory of unsecured consumer credit with risk of default","volume":"75","author":"Chatterjee","year":"2007","journal-title":"Econometrica"},{"key":"2026060112023817900_b10-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"785","DOI":"10.1145\/2939672.2939785","article-title":"Xgboost: A scalable tree boosting system","author":"Chen","year":"2016"},{"key":"2026060112023817900_b11-12_ra_10_25300_misq_2025_18080","unstructured":"Chen, Y.\n           (2023). Machine learning and optimization with latent variables [Unpublished doctoral dissertation]. Princeton University."},{"key":"2026060112023817900_b12-12_ra_10_25300_misq_2025_18080","unstructured":"Cox, J.\n           (2021). Household debt rises to $14.6 trillion due to record-breaking rise in mortgage loans. CNBC. https:\/\/www.cnbc.com\/2021\/02\/17\/household-debt-rises-to-14point6-trillion-due-to-record-breaking-rise-in-mortgage-loans"},{"issue":"6","key":"2026060112023817900_b13-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1111\/j.1937-5956.2010.01152.x","article-title":"Optimizing the collections process in consumer credit","volume":"19","author":"De Almeida Filho","year":"2010","journal-title":"Production and Operations Management"},{"key":"2026060112023817900_b14-12_ra_10_25300_misq_2025_18080","first-page":"973","article-title":"The foundations of cost-sensitive learning","author":"Elkan","year":"2001"},{"issue":"1","key":"2026060112023817900_b15-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"128","DOI":"10.1287\/isre.1120.0461","article-title":"Predicting adoption probabilities in social networks","volume":"24","author":"Fang","year":"2013","journal-title":"Information Systems Research"},{"issue":"2","key":"2026060112023817900_b16-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"517","DOI":"10.1016\/j.ejor.2015.07.013","article-title":"Spatial dependence in credit risk and its improvement in credit scoring","volume":"249","author":"Fernandes","year":"2016","journal-title":"European Journal of Operational Research"},{"issue":"1","key":"2026060112023817900_b17-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1006\/jcss.1997.1504","article-title":"A decision-theoretic generalization of on-line learning and an application to boosting","volume":"55","author":"Freund","year":"1997","journal-title":"Journal of Computer and System Sciences"},{"issue":"5","key":"2026060112023817900_b18-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"1189","DOI":"10.1214\/aos\/1013203451","article-title":"Greedy function approximation: A gradient boosting machine","volume":"29","author":"Friedman","year":"2001","journal-title":"The Annals of Statistics"},{"issue":"2","key":"2026060112023817900_b19-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1080\/08982112.2019.1655159","article-title":"Network based credit risk models","volume":"32","author":"Giudici","year":"2019","journal-title":"Quality Engineering"},{"key":"2026060112023817900_b20-12_ra_10_25300_misq_2025_18080","volume-title":"Deep learning","author":"Goodfellow","year":"2016"},{"issue":"2","key":"2026060112023817900_b21-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"417","DOI":"10.1016\/j.ejor.2015.05.050","article-title":"Instance-based credit risk assessment for investment decisions in P2P lending","volume":"249","author":"Guo","year":"2016","journal-title":"European Journal of Operational Research"},{"issue":"2","key":"2026060112023817900_b22-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1093\/imaman\/12.2.139","article-title":"Modelling consumer credit risk","volume":"12","author":"Hand","year":"2001","journal-title":"IMA Journal of Management Mathematics"},{"issue":"3","key":"2026060112023817900_b23-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"523","DOI":"10.1111\/j.1467-985X.1997.00078.x","article-title":"Statistical classification methods in consumer credit scoring: a review","volume":"160","author":"Hand","year":"1997","journal-title":"Journal of the Royal Statistical Society: Series A (Statistics in Society)"},{"issue":"9-10","key":"2026060112023817900_b24-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"1555","DOI":"10.1016\/S0167-8655(02)00394-X","article-title":"Choosing k for two-class nearest neighbour classifiers with unbalanced classes","volume":"24","author":"Hand","year":"2003","journal-title":"Pattern Recognition Letters"},{"issue":"1","key":"2026060112023817900_b25-12_ra_10_25300_misq_2025_18080","first-page":"3367","article-title":"Matrix completion and low-rank SVD via fast alternating least squares","volume":"16","author":"Hastie","year":"2015","journal-title":"The Journal of Machine Learning Research"},{"key":"2026060112023817900_b26-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7","volume-title":"The elements of statistical learning: data mining, inference and prediction","author":"Hastie","year":"2009","edition":"2nd"},{"issue":"1","key":"2026060112023817900_b27-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"77","DOI":"10.2307\/2348414","article-title":"A k-nearest-neighbour classifier for assessing consumer credit risk","volume":"45","author":"Henley","year":"1996","journal-title":"Journal of the Royal Statistical Society: Series D (The Statistician)"},{"key":"2026060112023817900_b28-12_ra_10_25300_misq_2025_18080","unstructured":"Horymski, C.\n           (2025). What is the average number of credit cards? Experian. https:\/\/www.experian.com\/blogs\/ask-experian\/average-number-of-credit-cards-a-person-has\/"},{"issue":"4","key":"2026060112023817900_b29-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"513","DOI":"10.1057\/jors.2011.30","article-title":"Using semi-supervised classifiers for credit scoring","volume":"64","author":"Kennedy","year":"2013","journal-title":"Journal of the Operational Research Society"},{"issue":"11","key":"2026060112023817900_b30-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"2767","DOI":"10.1016\/j.jbankfin.2010.06.001","article-title":"Consumer credit-risk models via machine-learning algorithms","volume":"34","author":"Khandani","year":"2010","journal-title":"Journal of Banking & Finance"},{"key":"2026060112023817900_b31-12_ra_10_25300_misq_2025_18080","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2017"},{"key":"2026060112023817900_b32-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114411","article-title":"Graph convolutional network-based credit default prediction utilizing three types of virtual distances among borrowers","volume":"168","author":"Lee","year":"2021","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"2026060112023817900_b33-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.ejor.2015.05.030","article-title":"Benchmarking state-of-the-art classification algorithms for credit scoring: An update of research","volume":"247","author":"Lessmann","year":"2015","journal-title":"European Journal of Operational Research"},{"issue":"4","key":"2026060112023817900_b34-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"1517","DOI":"10.25300\/MISQ\/2023\/17330","article-title":"Profit vs. equality? The case of financial risk assessment and a new perspective on alternative data","volume":"47","author":"Lu","year":"2023","journal-title":"MIS Quarterly"},{"issue":"2","key":"2026060112023817900_b35-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1016\/S0305-0483(03)00016-1","article-title":"Evaluating consumer loans using neural networks","volume":"31","author":"Malhotra","year":"2003","journal-title":"Omega"},{"issue":"1","key":"2026060112023817900_b36-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1146\/annurev.soc.27.1.415","article-title":"Birds of a feather: Homophily in social networks","volume":"27","author":"McPherson","year":"2001","journal-title":"Annual Review of Sociology"},{"issue":"3","key":"2026060112023817900_b37-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"1071","DOI":"10.1016\/j.ijforecast.2021.05.009","article-title":"Spatial dependence in microfinance credit default","volume":"38","author":"Medina-Olivares","year":"2022","journal-title":"International Journal of Forecasting"},{"key":"2026060112023817900_b38-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"437","DOI":"10.1007\/978-3-642-23783-6_28","article-title":"Link prediction via matrix factorization","author":"Menon","year":"2011"},{"key":"2026060112023817900_b39-12_ra_10_25300_misq_2025_18080","first-page":"1276","article-title":"Nonparametric latent feature models for link prediction","author":"Miller","year":"2009"},{"key":"2026060112023817900_b40-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"1101","DOI":"10.1109\/ICDM.2016.0143","article-title":"Optimizing the multiclass F-measure via biconcave programming","author":"Narasimhan","year":"2016"},{"key":"2026060112023817900_b41-12_ra_10_25300_misq_2025_18080","volume-title":"Numerical optimization","author":"Nocedal","year":"2006","edition":"2nd"},{"issue":"1","key":"2026060112023817900_b42-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","DOI":"10.25300\/MISQ\/2022\/461E1","article-title":"Editor\u2019s comments: Machine learning in information systems research","volume":"46","author":"Padmanabhan","year":"2022","journal-title":"MIS Quarterly"},{"issue":"2","key":"2026060112023817900_b43-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"490","DOI":"10.1016\/j.ejor.2009.03.008","article-title":"Subagging for credit scoring models","volume":"201","author":"Paleologo","year":"2010","journal-title":"European Journal of Operational Research"},{"key":"2026060112023817900_b44-12_ra_10_25300_misq_2025_18080","volume-title":"Numerical recipes: The art of scientific computing","author":"Press","year":"2007","edition":"3rd"},{"issue":"1","key":"2026060112023817900_b45-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"crossref","DOI":"10.25300\/MISQ\/2017\/41.1.E0","article-title":"Editor\u2019s comments: Diversity of design science research","volume":"41","author":"Rai","year":"2017","journal-title":"MIS Quarterly"},{"issue":"3","key":"2026060112023817900_b46-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"249","DOI":"10.1080\/07421222.2004.11045815","article-title":"Evaluating and tuning predictive data mining models using receiver operating characteristic curves","volume":"21","author":"Sinha","year":"2004","journal-title":"Journal of Management Information Systems"},{"issue":"3","key":"2026060112023817900_b47-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"199","DOI":"10.1023\/b:stco.0000035301.49549.88","article-title":"A tutorial on support vector regression","volume":"14","author":"Smola","year":"2004","journal-title":"Statistics and Computing"},{"key":"2026060112023817900_b48-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"46","DOI":"10.3115\/v1\/D14-1006","article-title":"Identifying argumentative discourse structures in persuasive essays","author":"Stab","year":"2014"},{"key":"2026060112023817900_b49-12_ra_10_25300_misq_2025_18080","unstructured":"Stolba, S. L.\n           (2019). How do credit card companies make money? Experian. https:\/\/www.experian.com\/blogs\/ask-experian\/how-do-credit-card-companies-make-money\/"},{"key":"2026060112023817900_b50-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"crossref","DOI":"10.1137\/1.9781611974560","volume-title":"Credit scoring and its applications","author":"Thomas","year":"2017","edition":"2nd"},{"issue":"2","key":"2026060112023817900_b51-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"149","DOI":"10.1016\/S0169-2070(00)00034-0","article-title":"A survey of credit and behavioural scoring: forecasting financial risk of lending to consumers","volume":"16","author":"Thomas","year":"2000","journal-title":"International Journal of Forecasting"},{"issue":"4","key":"2026060112023817900_b52-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"3326","DOI":"10.1016\/j.eswa.2009.10.018","article-title":"Multiple classifier application to credit risk assessment","volume":"37","author":"Twala","year":"2010","journal-title":"Expert Systems with Applications"},{"issue":"1","key":"2026060112023817900_b53-12_ra_10_25300_misq_2025_18080","first-page":"5","article-title":"An overview of composite likelihood methods","volume":"21","author":"Varin","year":"2011","journal-title":"Statistica Sinica"},{"key":"2026060112023817900_b54-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"702","DOI":"10.1137\/1.9781611976700.79","article-title":"Temporal-aware graph neural network for credit risk prediction","author":"Wang","year":"2021"},{"issue":"10","key":"2026060112023817900_b55-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"2543","DOI":"10.1016\/j.cor.2004.03.017","article-title":"Neural network ensemble strategies for financial decision applications","volume":"32","author":"West","year":"2005","journal-title":"Computers & Operations Research"},{"issue":"2","key":"2026060112023817900_b56-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"676","DOI":"10.1287\/ijoc.2023.0115","article-title":"Toward graph data collaboration in a data-sharing-free manner: A novel privacy-preserving graph pretraining model","volume":"38","author":"Xu","year":"2025","journal-title":"INFORMS Journal on Computing"},{"issue":"1","key":"2026060112023817900_b57-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"810","DOI":"10.1109\/tkde.2021.3091022","article-title":"Netrl: Task-aware network denoising via deep reinforcement learning","volume":"35","author":"Xu","year":"2023","journal-title":"IEEE Transactions on Knowledge and Data Engineering"},{"issue":"2","key":"2026060112023817900_b58-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"351","DOI":"10.1287\/isre.2018.0805","article-title":"Prescribing response strategies to manage customer opinions: A stochastic differential equation approach","volume":"30","author":"Yang","year":"2019","journal-title":"Information Systems Research"},{"issue":"2","key":"2026060112023817900_b59-12_ra_10_25300_misq_2025_18080","doi-asserted-by":"publisher","first-page":"528","DOI":"10.1016\/j.ejor.2014.06.043","article-title":"Support vector regression for loss given default modelling","volume":"240","author":"Yao","year":"2015","journal-title":"European Journal of Operational Research"}],"container-title":["MIS Quarterly"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/misq.umn.edu\/misq\/article-pdf\/50\/2\/731\/20604\/12_ra_10.25300_misq_2025_18080.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/misq.umn.edu\/misq\/article-pdf\/50\/2\/731\/20604\/12_ra_10.25300_misq_2025_18080.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,1]],"date-time":"2026-06-01T16:02:48Z","timestamp":1780329768000},"score":1,"resource":{"primary":{"URL":"https:\/\/misq.umn.edu\/misq\/article\/50\/2\/731\/3618\/Latent-Similarity-Enhanced-Credit-Risk-Prediction1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,1]]},"references-count":59,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,6,1]]},"published-print":{"date-parts":[[2026,6,1]]}},"URL":"https:\/\/doi.org\/10.25300\/misq\/2025\/18080","relation":{},"ISSN":["0276-7783","2162-9730"],"issn-type":[{"value":"0276-7783","type":"print"},{"value":"2162-9730","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,1]]}}}