{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T05:59:42Z","timestamp":1790315982826,"version":"4.1.0"},"reference-count":68,"publisher":"Wiley","issue":"3","license":[{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:00:00Z","timestamp":1783209600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Intelligent Sys in Account"],"published-print":{"date-parts":[[2026,9]]},"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:p>The advent of artificial intelligence has significantly enhanced credit\u2010scoring technologies. Despite the remarkable efficacy of advanced deep learning models, mainstream adoption continues to favor tree\u2010structured models due to their robust predictive performance on tabular data. Although pretrained models have seen considerable development, the use of such models for tabular\u2010structured credit\u2010scoring datasets remains largely unexplored. Tabular\u2010oriented large models, such as TabPFN, have made the application of large models in credit\u2010scoring feasible, albeit they can only process limited sample sizes. This paper proposes a novel framework that combines a tabular\u2010tailored dataset distillation technique with a pretrained model, thereby improving the scalability of TabPFN. Furthermore, although class imbalance is a common characteristic of financial datasets, its influence during dataset distillation has not been systematically explored; we therefore integrate imbalance\u2010aware objectives into the distillation process, resulting in improved performance on imbalanced credit data. Experiments on six publicly available credit\u2010scoring datasets show that the proposed imbalance\u2010aware distillation improves AUC by up to 8.7 percentage points over the standard MSE\u2010based distillation baseline. At the same time, distilled datasets retain roughly 76%\u201395% of the full\u2010data AUC while often using under 10% of the original training samples (and at most 31.3%) and consistently outperforming random subsets. Taken together, these results demonstrate that imbalance\u2010aware dataset distillation provides a compact yet accurate solution for imbalanced credit scoring and enhances the practical scalability of tabular pretrained models such as TabPFN.<\/jats:p>","DOI":"10.1002\/isaf.70042","type":"journal-article","created":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T04:22:43Z","timestamp":1783311763000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Class\u2010Imbalance\u2010Aware Adaptive Dataset Distillation for Scalable Pretrained Model in Credit Scoring"],"prefix":"10.1002","volume":"33","author":[{"given":"Xia","family":"Li","sequence":"first","affiliation":[{"name":"Risk Management Division China Development Bank  Beijing China"},{"name":"University of Cambridge  Cambridge"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanghang","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Finance Central University of Finance and Economics  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiwei","family":"Zhuang","sequence":"additional","affiliation":[{"name":"Risk Management Division China Development Bank  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhong","family":"Wang","sequence":"additional","affiliation":[{"name":"Risk Management Division China Development Bank  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Chen","sequence":"additional","affiliation":[{"name":"Risk Management Division China Development Bank  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong","family":"Liu","sequence":"additional","affiliation":[{"name":"Risk Management Division China Development Bank  Beijing China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jasmine","family":"Bai","sequence":"additional","affiliation":[{"name":"GF Holdings (Hong Kong) Corporation Limited  Hong Kong SAR China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mao","family":"Mao","sequence":"additional","affiliation":[{"name":"GF Holdings (Hong Kong) Corporation Limited  Hong Kong SAR China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,7,5]]},"reference":[{"key":"e_1_2_11_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3357091"},{"key":"e_1_2_11_3_1","doi-asserted-by":"publisher","DOI":"10.3390\/app13042272"},{"key":"e_1_2_11_4_1","volume-title":"Advanced Credit Card Fraud Detection: An Ensemble Learning Using Random Under Sampling and Two\u2010Stage Thresholding","author":"Almubark I.","year":"2024"},{"key":"e_1_2_11_5_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2015.07.062"},{"key":"e_1_2_11_6_1","doi-asserted-by":"publisher","DOI":"10.1057\/jors.2008.130"},{"key":"e_1_2_11_7_1","doi-asserted-by":"publisher","DOI":"10.1002\/isaf.261"},{"key":"e_1_2_11_8_1","first-page":"1567","article-title":"Learning Imbalanced Datasets With Label\u2010Distribution\u2010Aware Margin Loss","volume":"32","author":"Cao K.","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_11_9_1","doi-asserted-by":"publisher","DOI":"10.1080\/14765284.2023.2212434"},{"key":"e_1_2_11_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2939672.2939785"},{"key":"e_1_2_11_11_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.fmre.2021.08.017"},{"key":"e_1_2_11_12_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2020.106263"},{"issue":"15","key":"e_1_2_11_13_1","first-page":"185","article-title":"Explainable AI for Interpretable Credit Scoring","volume":"10","author":"Demajo L. M.","year":"2020","journal-title":"Computer Science & Information Technology"},{"key":"e_1_2_11_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ComPE49325.2020.9200087"},{"key":"e_1_2_11_15_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1423"},{"key":"e_1_2_11_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2021.06.053"},{"key":"e_1_2_11_17_1","first-page":"2016","article-title":"Classification of Imbalance Data Using Tomek Link (T\u2010Link) Combined With Random Under\u2010Sampling (RUS) as a Data Reduction Method","volume":"1","author":"Elhassan T.","year":"2016","journal-title":"Global Journal of Technology and Optimization"},{"key":"e_1_2_11_18_1","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.11192"},{"key":"e_1_2_11_19_1","volume-title":"2nd Table Representation Learning Workshop","author":"Feuer B.","year":"2023"},{"issue":"11","key":"e_1_2_11_20_1","first-page":"11891","article-title":"Preserving Privacy in Federated Learning With Ensemble Cross\u2010Domain Knowledge Distillation","volume":"36","author":"Gong X.","year":"2022","journal-title":"Paper Presented at the Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"e_1_2_11_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICACCI.2017.8125820"},{"key":"e_1_2_11_22_1","volume-title":"Paper Presented at the 2008 IEEE International Joint Conference on Neural Networks (IEEE World Congress on Computational Intelligence)","author":"He H.","year":"2008"},{"key":"e_1_2_11_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.239"},{"key":"e_1_2_11_24_1","article-title":"BERT\u2010Based Financial Sentiment Index and LSTM\u2010Based Stock Return Predictability","author":"Hiew J. Z. G.","year":"2019","journal-title":"arXiv Preprint"},{"key":"e_1_2_11_25_1","volume-title":"International Conference on Learning Representations","author":"Hollmann N.","year":"2022"},{"key":"e_1_2_11_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cam.2020.113065"},{"key":"e_1_2_11_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10614-020-09975-3"},{"key":"e_1_2_11_28_1","volume-title":"Paper Presented at the 2021 IEEE 1st International Conference on Digital Twins and Parallel Intelligence (DTPI)","author":"Jing R.","year":"2021"},{"issue":"21","key":"e_1_2_11_29_1","first-page":"23533","article-title":"Effective Data Distillation for Tabular Datasets (Student Abstract)","volume":"38","author":"Kang I.","year":"2024","journal-title":"Paper Presented at the Proceedings of the AAAI Conference on Artificial Intelligence"},{"key":"e_1_2_11_30_1","volume-title":"Paper Presented at the Proceedings of the 31st International Conference on Neural Information Processing Systems","author":"Ke G.","year":"2017"},{"key":"e_1_2_11_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_36"},{"key":"e_1_2_11_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3086230"},{"key":"e_1_2_11_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3322540"},{"key":"e_1_2_11_34_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.frl.2023.104867"},{"key":"e_1_2_11_35_1","article-title":"Implementation of an Asymmetric Adjusted Activation Function for Class Imbalance Credit Scoring","author":"Li X.","year":"2025","journal-title":"arXiv Preprint"},{"key":"e_1_2_11_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/s41060-021-00279-9"},{"key":"e_1_2_11_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"e_1_2_11_38_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0317726"},{"key":"e_1_2_11_39_1","first-page":"40043","volume-title":"Proceedings of the 42nd International Conference on Machine Learning","author":"Liu S.\u2010Y.","year":"2025"},{"key":"e_1_2_11_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118158"},{"key":"e_1_2_11_41_1","article-title":"Roberta: A Robustly Optimized Bert Pretraining Approach","author":"Liu Y.","year":"2019","journal-title":"arXiv Preprint"},{"key":"e_1_2_11_42_1","doi-asserted-by":"publisher","DOI":"10.1002\/isaf.70014"},{"key":"e_1_2_11_43_1","article-title":"Machine Learning for Synthetic Data Generation: A Review","author":"Lu Y.","year":"2023","journal-title":"arXiv Preprint"},{"key":"e_1_2_11_44_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2023.3331100"},{"key":"e_1_2_11_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113986"},{"key":"e_1_2_11_46_1","doi-asserted-by":"publisher","DOI":"10.1002\/isaf.70005"},{"key":"e_1_2_11_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.121876"},{"key":"e_1_2_11_48_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.119640"},{"key":"e_1_2_11_49_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Nguyen T.","year":"2020"},{"key":"e_1_2_11_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2024.3508804"},{"key":"e_1_2_11_51_1","doi-asserted-by":"publisher","DOI":"10.1002\/isaf.1521"},{"key":"e_1_2_11_52_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110414"},{"key":"e_1_2_11_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-024-06166-x"},{"key":"e_1_2_11_54_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2021.11.011"},{"key":"e_1_2_11_55_1","doi-asserted-by":"publisher","DOI":"10.1002\/isaf.1437"},{"key":"e_1_2_11_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2023.3240968"},{"key":"e_1_2_11_57_1","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611974560"},{"key":"e_1_2_11_58_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.techsoc.2020.101413"},{"key":"e_1_2_11_59_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.05.035"},{"key":"e_1_2_11_60_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.06.069"},{"key":"e_1_2_11_61_1","article-title":"BloombergGPT: A Large Language Model for Finance","author":"Wu S.","year":"2023","journal-title":"arXiv Preprint"},{"key":"e_1_2_11_62_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Xu D.","year":"2024"},{"key":"e_1_2_11_63_1","doi-asserted-by":"publisher","DOI":"10.2139\/ssrn.4489826"},{"key":"e_1_2_11_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3323376"},{"key":"e_1_2_11_65_1","doi-asserted-by":"publisher","DOI":"10.1155\/2022\/8612759"},{"key":"e_1_2_11_66_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR)","author":"Zhao B.","year":"2020"},{"key":"e_1_2_11_67_1","article-title":"Revolutionizing Finance With LLMs: An Overview of Applications and Insights","author":"Zhao H.","year":"2024","journal-title":"arXiv Preprint"},{"key":"e_1_2_11_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CSCWD49262.2021.9437616"},{"key":"e_1_2_11_69_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2021.107672"}],"container-title":["Intelligent Systems in Accounting, Finance and Management"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/isaf.70042","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1002\/isaf.70042","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/isaf.70042","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,25]],"date-time":"2026-09-25T05:28:12Z","timestamp":1790314092000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/isaf.70042"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,5]]},"references-count":68,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["10.1002\/isaf.70042"],"URL":"https:\/\/doi.org\/10.1002\/isaf.70042","archive":["Portico"],"relation":{},"ISSN":["1550-1949","2160-0074"],"issn-type":[{"value":"1550-1949","type":"print"},{"value":"2160-0074","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,5]]},"assertion":[{"value":"2025-07-07","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-06-19","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-07-05","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70042"}}