{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,2]],"date-time":"2026-05-02T07:02:26Z","timestamp":1777705346073,"version":"3.51.4"},"reference-count":38,"publisher":"SAGE Publications","issue":"4","license":[{"start":{"date-parts":[[2021,5,14]],"date-time":"2021-05-14T00:00:00Z","timestamp":1620950400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/journals.sagepub.com\/page\/policies\/text-and-data-mining-license"}],"content-domain":{"domain":["journals.sagepub.com"],"crossmark-restriction":true},"short-container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"published-print":{"date-parts":[[2021,11,4]]},"abstract":"<jats:p>To deal with the systematic risk of financial institutions and the rapid increasing of loan applications, it is becoming extremely important to automatically predict the default probability of a loan. However, this task is non-trivial due to the insufficient default samples, hard decision boundaries and numerous heterogeneous features. To the best of our knowledge, existing related researches fail in handling these three difficulties simultaneously. In this paper, we propose a weakly supervised loan default prediction model WEAKLOAN that systematically solves all these challenges based on deep metric learning. WEAKLOAN is composed of three key modules which are used for encoding loan features, learning evaluation metrics and calculating default risk scores. By doing so, WEAKLOAN can not only extract the features of a loan itself, but also model the hidden relationships in loan pairs. Extensive experiments on real-life datasets show that WEAKLOAN significantly outperforms all compared baselines even though the default loans for training are limited.<\/jats:p>","DOI":"10.3233\/jifs-189987","type":"journal-article","created":{"date-parts":[[2021,5,18]],"date-time":"2021-05-18T13:39:59Z","timestamp":1621345199000},"page":"5007-5019","update-policy":"https:\/\/doi.org\/10.1177\/sage-journals-update-policy","source":"Crossref","is-referenced-by-count":2,"title":["A deep metric learning approach for weakly supervised loan default prediction"],"prefix":"10.1177","volume":"41","author":[{"given":"Kai","family":"Zhuang","sequence":"first","affiliation":[{"name":"School of Economics and Management, University of Science and Technology Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sen","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Economics and Management, University of Science and Technology Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaonan","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Economics and Management, University of Science and Technology Beijing, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","published-online":{"date-parts":[[2021,5,14]]},"reference":[{"key":"e_1_3_1_2_2","article-title":"A survey on metric learning for feature vectors and structured data, arXiv preprint arXiv:","author":"Bellet A.","year":"2013","unstructured":"BelletA., HabrardA. and SebbanM., A survey on metric learning for feature vectors and structured data, arXiv preprint arXiv:, 1306.6709 (2013).","journal-title":"1306.6709"},{"key":"e_1_3_1_3_2","first-page":"719","article-title":"Predicting credit risk in peer-to-peer lending a neural network approach","author":"Byanjankar A.","year":"2015","unstructured":"ByanjankarA., Heikkil\u00e4M. and MezeiJ., Predicting credit risk in peer-to-peer lending a neural network approach, Proceedings of the IEEE Symposium Series on Computational Intelligence (2015), 719\u2013725.","journal-title":"Proceedings of the IEEE Symposium Series on Computational Intelligence"},{"key":"e_1_3_1_4_2","doi-asserted-by":"publisher","DOI":"10.24818\/18423264\/53.2.19.09"},{"key":"e_1_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbankfin.2010.06.001"},{"key":"e_1_3_1_6_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2019.02.014"},{"key":"e_1_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jbusres.2018.02.008"},{"key":"e_1_3_1_8_2","doi-asserted-by":"publisher","DOI":"10.1561\/2200000019"},{"key":"e_1_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1057\/jors.2014.50"},{"key":"e_1_3_1_10_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2006.07.007"},{"key":"e_1_3_1_11_2","first-page":"5375","article-title":"Loy and X. Tang, Learning deep representation for imbalanced classification","author":"Huang C.","year":"2016","unstructured":"HuangC., LiY. and ChangeC., Loy and X. Tang, Learning deep representation for imbalanced classification, Proceedings of the IEEE conference on computer vision and pattern recognition (2016), 5375\u20135384.","journal-title":"Proceedings of the IEEE conference on computer vision and pattern recognition"},{"key":"e_1_3_1_12_2","first-page":"39","article-title":"Weakly supervised deep metric learning for template matching","volume":"943","author":"Buniatyan D.","year":"2020","unstructured":"BuniatyanD., PopovychS., IhD., MacrinaT., ZungJ. and SeungH.S., Weakly supervised deep metric learning for template matching, Advances in Computer Vision943 (2020), 39\u201358.","journal-title":"Advances in Computer Vision"},{"key":"e_1_3_1_13_2","article-title":"Adam: A method for stochastic optimization","author":"Kingma D.P.","year":"2015","unstructured":"KingmaD.P. and BaJ., Adam: A method for stochastic optimization, Proceedings of the International Conference on Learning Representations (2015).","journal-title":"Proceedings of the International Conference on Learning Representations"},{"key":"e_1_3_1_14_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2020.01.033"},{"key":"e_1_3_1_15_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24261-3_7"},{"key":"e_1_3_1_16_2","unstructured":"PangG. HengelA.V.D. and ShenC. Weakly supervised deep anomaly detection with pairwise relation learning arXiv:1 a) (2019)."},{"key":"e_1_3_1_17_2","unstructured":"PangG. ShenC. JinH. and HengelA.V.D. Deep weaklysupervised anomaly detection arXiv:1 b) (2019)."},{"key":"e_1_3_1_18_2","first-page":"5382","article-title":"Deep metric learning via facility location","author":"Song H.O.","year":"2017","unstructured":"SongH.O., JegelkaS., RathodV. and MurphyK., Deep metric learning via facility location, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2017), 5382\u20135390.","journal-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition"},{"issue":"40","key":"e_1_3_1_19_2","article-title":"On ensemble ssl algorithms for credit scoring problem","volume":"5","author":"Livieris I.E.","year":"2018","unstructured":"LivierisI.E., KiriakidouN., KanavosA., TampakasV. and PintelasP., On ensemble ssl algorithms for credit scoring problem, Informatics5(40) (2018).","journal-title":"Informatics"},{"key":"e_1_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1287\/mnsc.2017.2947"},{"key":"e_1_3_1_21_2","unstructured":"DevlinJ. ChangM.W. LeeK. and ToutanovaK. Bert: Pretraining of deep bidirectional transformers for language understanding arXiv preprint arXiv:5 (2018)."},{"key":"e_1_3_1_22_2","first-page":"1532","article-title":"Glove: Global vectors for word representation","author":"Pennington J.","year":"2014","unstructured":"PenningtonJ., SocherR. and ManningC.D., Glove: Global vectors for word representation, Proceedings of the conference on empirical methods in natural language processing (2014), 1532\u20131543.","journal-title":"Proceedings of the conference on empirical methods in natural language processing"},{"key":"e_1_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2019.105118"},{"key":"e_1_3_1_24_2","doi-asserted-by":"publisher","DOI":"10.1057\/jors.2011.30"},{"key":"e_1_3_1_25_2","article-title":"Distance metric learning: A comprehensive survey, Ph.D. Dissertation","author":"Yang L.","year":"2006","unstructured":"YangL. and JinR., Distance metric learning: A comprehensive survey, Ph.D. Dissertation, Michigan State University (2006).","journal-title":"Michigan State University"},{"key":"e_1_3_1_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.comcom.2020.01.016"},{"key":"e_1_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2011.01.096"},{"key":"e_1_3_1_28_2","doi-asserted-by":"publisher","DOI":"10.1057\/palgrave.jors.2601922"},{"key":"e_1_3_1_29_2","article-title":"Papers","author":"Odegua R.","year":"2020","unstructured":"OdeguaR., Papers, Predicting bank loan default with extreme gradient boosting (2020).","journal-title":"Predicting bank loan default with extreme gradient boosting"},{"key":"e_1_3_1_30_2","first-page":"558","article-title":"A semi-supervised approach for reject inference in credit scoring using svms","author":"Maldonado S.","year":"2010","unstructured":"MaldonadoS. and ParedesG., A semi-supervised approach for reject inference in credit scoring using svms, Proceedings of the Industrial Conference on Data Mining (2010), 558\u2013571.","journal-title":"Proceedings of the Industrial Conference on Data Mining"},{"key":"e_1_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2015.09.014"},{"key":"e_1_3_1_32_2","first-page":"5528","article-title":"Extensions of recurrent neural network language model","author":"Mikolov T.","year":"2011","unstructured":"MikolovT., KombrinkS., BurgetL., Cernock\u2018yJ. and KhudanpurS., Extensions of recurrent neural network language model, Proceedings of the IEEE international conference on acoustics, speech and signal processing (2011), 5528\u20135531.","journal-title":"Proceedings of the IEEE international conference on acoustics, speech and signal processing"},{"key":"e_1_3_1_33_2","first-page":"635","article-title":"Semi-supervised anti-fraud models for cash pre-loan in internet consumer finance","author":"Sun W.","year":"2019","unstructured":"SunW., ChenM., YeJ.X., ZhangY., XuC.Z., ZhangY., WangY., WuW., ZhangP. and QuF., Semi-supervised anti-fraud models for cash pre-loan in internet consumer finance, Proceedings of the IEEE International Conference on Industrial Cyber Physical Systems (2019), 635\u2013640.","journal-title":"Proceedings of the IEEE International Conference on Industrial Cyber Physical Systems"},{"key":"e_1_3_1_34_2","first-page":"1859","article-title":"Overdue prediction of bank loans based on LSTM-SVM","author":"Li X.","year":"2018","unstructured":"LiX., LongX., SunG., YangG. and LiH., Overdue prediction of bank loans based on LSTM-SVM, Proceedings of the IEEE Smart-World (2018), 1859\u20131863.","journal-title":"Proceedings of the IEEE Smart-World"},{"key":"e_1_3_1_35_2","first-page":"277","article-title":"Fraud risk measurement of basic medical insurance for urban and rural residents in china","volume":"53","author":"Liu X.","year":"2019","unstructured":"LiuX., ZhangX. and YangX., Fraud risk measurement of basic medical insurance for urban and rural residents in china, Economic Computation and Economic Cybernetics Studies and Research \/ Academy of Economic Studies53 (2019), 277\u2013296.","journal-title":"Economic Computation and Economic Cybernetics Studies and Research \/ Academy of Economic Studies"},{"key":"e_1_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"e_1_3_1_37_2","first-page":"240","article-title":"Loan default prediction using diversified sensitivity undersampling","author":"Chen Y.","year":"2018","unstructured":"ChenY., ZhangJ. and NgW.W.Y., Loan default prediction using diversified sensitivity undersampling, Proceedings of the International Conference on Machine Learning and Cybernetics (2018), 240\u2013245.","journal-title":"Proceedings of the International Conference on Machine Learning and Cybernetics"},{"key":"e_1_3_1_38_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2017.01.011"}],"container-title":["Journal of Intelligent &amp; Fuzzy Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-189987","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/full-xml\/10.3233\/JIFS-189987","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/journals.sagepub.com\/doi\/pdf\/10.3233\/JIFS-189987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T09:43:35Z","timestamp":1777455815000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.sagepub.com\/doi\/10.3233\/JIFS-189987"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,14]]},"references-count":38,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2021,11,4]]}},"alternative-id":["10.3233\/JIFS-189987"],"URL":"https:\/\/doi.org\/10.3233\/jifs-189987","relation":{},"ISSN":["1064-1246","1875-8967"],"issn-type":[{"value":"1064-1246","type":"print"},{"value":"1875-8967","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,14]]}}}