{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,25]],"date-time":"2026-04-25T14:12:20Z","timestamp":1777126340966,"version":"3.51.4"},"reference-count":58,"publisher":"MDPI AG","issue":"1","license":[{"start":{"date-parts":[[2025,12,21]],"date-time":"2025-12-21T00:00:00Z","timestamp":1766275200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003847","name":"Ningbo Municipal Government","doi-asserted-by":"publisher","award":["2021B-008-C"],"award-info":[{"award-number":["2021B-008-C"]}],"id":[{"id":"10.13039\/501100003847","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Information"],"abstract":"<jats:p>Credit risk refers to the possibility that a borrower fails to meet contractual repayment obligations, posing potential losses to lenders. This study aims to enhance post-loan default prediction in credit risk management by constructing a time-series modeling framework based on repayment behavior data, enabling the capture of repayment risks that emerge after loan issuance. To achieve this objective, a Residual Enhanced Encoder Bidirectional Long Short-Term Memory (ResE-BiLSTM) model is proposed, in which the attention mechanism is responsible for discovering long-range correlations, while the residual connections ensure the preservation of distant information. This design mitigates the tendency of conventional recurrent architectures to overemphasize recent inputs while underrepresenting distant temporal information in long-term dependency modeling. Using the real-world large-scale Freddie Mac Single-Family Loan-Level Dataset, the model is evaluated on 44 independent cohorts and compared with five baseline models, including Long Short-Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Gated Recurrent Unit (GRU), Convolutional Neural Network (CNN), and Recurrent Neural Network (RNN) across multiple evaluation metrics. The experimental results demonstrate that ResE-BiLSTM achieves superior performance on key indicators such as F1 and AUC, with average values of 0.92 and 0.97, respectively, and demonstrates robust performance across different feature window lengths and resampling settings. Ablation experiments and SHapley Additive exPlanations (SHAP)-based interpretability analyses further reveal that the model captures non-monotonic temporal importance patterns across key financial features. This study advances time-series\u2013based anomaly detection for credit risk prediction by integrating global and local temporal learning. The findings offer practical value for financial institutions and risk management practitioners, while also providing methodological insights and a transferable modeling paradigm for future research on credit risk assessment.<\/jats:p>","DOI":"10.3390\/info17010005","type":"journal-article","created":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T14:27:47Z","timestamp":1766500067000},"page":"5","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Transforming Credit Risk Analysis: A Time-Series-Driven ResE-BiLSTM Framework for Post-Loan Default Detection"],"prefix":"10.3390","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5755-5395","authenticated-orcid":false,"given":"Yue","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science, University of Nottingham Ningbo China, Ningbo 315100, China"}]},{"given":"Yuxiang","family":"Lin","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Nottingham Ningbo China, Ningbo 315100, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-2900-9197","authenticated-orcid":false,"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Mathematical Sciences, University of Nottingham Ningbo China, Ningbo 315100, China"}]},{"given":"Zihan","family":"Su","sequence":"additional","affiliation":[{"name":"Department of Mathematical Sciences, University of Nottingham Ningbo China, Ningbo 315100, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8302-5172","authenticated-orcid":false,"given":"Chang Chuan","family":"Goh","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Nottingham Ningbo China, Ningbo 315100, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5882-1265","authenticated-orcid":false,"given":"Tangtangfang","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Nottingham Ningbo China, Ningbo 315100, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6317-5877","authenticated-orcid":false,"given":"Anthony","family":"Bellotti","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Nottingham Ningbo China, Ningbo 315100, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5743-1010","authenticated-orcid":false,"given":"Boon Giin","family":"Lee","sequence":"additional","affiliation":[{"name":"School of Computer Science, University of Nottingham Ningbo China, Ningbo 315100, China"}]}],"member":"1968","published-online":{"date-parts":[[2025,12,21]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"116429","DOI":"10.1016\/j.eswa.2021.116429","article-title":"Financial Fraud: A Review of Anomaly Detection Techniques and Recent Advances","volume":"193","author":"Hilal","year":"2021","journal-title":"Expert Syst. Appl."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"100402","DOI":"10.1016\/j.cosrev.2021.100402","article-title":"Financial fraud detection applying data mining techniques: A comprehensive review from 2009 to 2019","volume":"40","author":"Magalingam","year":"2021","journal-title":"Comput. Sci. Rev."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Goh, C.C., Yang, Y., Bellotti, A., and Hua, X. (2025). Machine Learning for Chinese Corporate Fraud Prediction: Segmented Models Based on Optimal Training Windows. Information, 16.","DOI":"10.3390\/info16050397"},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"2514","DOI":"10.1002\/ijfe.2284","article-title":"How fintech impacts pre- and post-loan risk in Chinese commercial banks","volume":"27","author":"Zhang","year":"2020","journal-title":"Int. J. Financ. Econ."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Gupta, A., Pant, V., Kumar, S., and Bansal, P.K. (2020, January 4\u20135). Bank Loan Prediction System using Machine Learning. Proceedings of the 2020 9th International Conference System Modeling and Advancement in Research Trends (SMART), Moradabad, India.","DOI":"10.1109\/SMART50582.2020.9336801"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"012042","DOI":"10.1088\/1757-899X\/1022\/1\/012042","article-title":"Loan default prediction using decision trees and random forest: A comparative study","volume":"1022","author":"Madaan","year":"2021","journal-title":"IOP Conf. Ser. Mater. Sci. Eng."},{"key":"ref_7","unstructured":"Elmasry, M. (2019). Machine Learning Approach for Credit Score Analysis: A Case Study of Predicting Mortgage Loan Defaults. [Master\u2019s Thesis, Universidade NOVA de Lisboa]."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"9942410","DOI":"10.1155\/2021\/9942410","article-title":"Prediction of Financial Time Series Based on LSTM Using Wavelet Transform and Singular Spectrum Analysis","volume":"2021","author":"Tang","year":"2021","journal-title":"Math. Probl. Eng."},{"key":"ref_9","doi-asserted-by":"crossref","unstructured":"Pardeshi, K., Gill, S.S., and Abdelmoniem, A.M. (2023). Stock Market Price Prediction: A Hybrid LSTM and Sequential Self-Attention based Approach. arXiv.","DOI":"10.1201\/9781003467199-11"},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"e1588","DOI":"10.7717\/peerj-cs.1588","article-title":"Rural micro-credit model design and credit risk assessment via improved LSTM algorithm","volume":"9","author":"Gao","year":"2023","journal-title":"PeerJ Comput. Sci."},{"key":"ref_11","unstructured":"Siami-Namini, S., Siami-Namini, S., Tavakoli, N., Tavakoli, N., Namin, A.S., and Namin, A.S. (2019). A Comparative Analysis of Forecasting Financial Time Series Using ARIMA, LSTM, and BiLSTM. arXiv."},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Siami-Namini, S., Tavakoli, N., and Namin, A.S. (2019, January 9\u201312). The Performance of LSTM and BiLSTM in Forecasting Time Series. Proceedings of the 2019 IEEE International Conference on Big Data (Big Data), Los Angeles, CA, USA.","DOI":"10.1109\/BigData47090.2019.9005997"},{"key":"ref_13","unstructured":"Ji, Y. (2021). Explainable AI Methods for Credit Card Fraud Detection: Evaluation of LIME and SHAP Through a User Study. [Master\u2019s Thesis, University of Sk\u00f6vde]."},{"key":"ref_14","doi-asserted-by":"crossref","unstructured":"Sai, C.V., Das, D., Elmitwally, N., Elezaj, O., and Islam, M.B. (2023). Explainable AI-Driven Financial Transaction Fraud Detection Using Machine Learning and Deep Neural Networks. SSRN, preprint.","DOI":"10.2139\/ssrn.4439980"},{"key":"ref_15","unstructured":"Mac, F. (2024, January 25). Freddie Mac Dataset. Available online: https:\/\/www.freddiemac.com\/research\/datasets\/sf-loanlevel-dataset."},{"key":"ref_16","unstructured":"Lundberg, S.M., and Lee, S.I. (2017, January 4\u20139). A Unified Approach to Interpreting Model Predictions. Proceedings of the Neural Information Processing Systems, Long Beach, CA, USA."},{"key":"ref_17","first-page":"23","article-title":"A Survey on Explainable Anomaly Detection","volume":"18","author":"Li","year":"2023","journal-title":"ACM Trans. Knowl. Discov. Data"},{"key":"ref_18","unstructured":"(2024, January 25). Lending-Club Dataset. Available online: https:\/\/github.com\/matmcreative\/Lending-Club-Loan-Analysis\/."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Zandi, S., Korangi, K., \u00d3skarsd\u00f3ttir, M., Mues, C., and Bravo, C. (2024). Attention-based Dynamic Multilayer Graph Neural Networks for Loan Default Prediction. arXiv.","DOI":"10.1016\/j.ejor.2024.09.025"},{"key":"ref_20","doi-asserted-by":"crossref","unstructured":"Wang, H., Bellotti, A., Qu, R., and Bai, R. (2024). Discrete-Time Survival Models with Neural Networks for Age\u2013Period\u2013Cohort Analysis of Credit Risk. Risks, 12.","DOI":"10.20944\/preprints202401.0040.v1"},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"21757","DOI":"10.1007\/s11042-023-14365-6","article-title":"An integration of deep learning model with Navo Minority Over-Sampling Technique to detect the frauds in credit cards","volume":"82","author":"Karthika","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Kanimozhi, P., Parkavi, S., and Kumar, T.A. (2023, January 21\u201322). Predicting Mortgage-Backed Securities Prepayment Risk Using Machine Learning Models. Proceedings of the 2023 2nd International Conference on Smart Technologies and Systems for Next Generation Computing (ICSTSN), Villupuram, India.","DOI":"10.1109\/ICSTSN57873.2023.10151481"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Qian, C., Hu, T., and Li, B. (2022, January 5\u20139). A BiLSTM-Attention Model for Detecting Smart Contract Defects More Accurately. Proceedings of the International Conference on Software Quality, Reliability and Security, Guangzhou, China.","DOI":"10.1109\/QRS57517.2022.00016"},{"key":"ref_24","first-page":"35","article-title":"Hybrid Sampling and Similarity Attention Layer in Bidirectional Long Short Term Memory in Credit Card Fraud Detection","volume":"15","author":"Narayan","year":"2022","journal-title":"Int. J. Intell. Eng. Syst."},{"key":"ref_25","first-page":"2552","article-title":"Hybrid CNN-BILSTM-Attention Based Identification and Prevention System for Banking Transactions","volume":"8","author":"Agarwal","year":"2021","journal-title":"Nat. Volatiles Essent. Oils"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Joy, B., and R, D. (2023, January 18\u201320). A Tensor Based Approach for Click Fraud Detection on Online Advertising Using BiLSTM and Attention based CNN. Proceedings of the 2023 International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS), Erode, India.","DOI":"10.1109\/ICSSAS57918.2023.10331862"},{"key":"ref_27","unstructured":"Prabhakar, K., Giridhar, M.S., Amrita, T., Joshi, T.M., Pal, S., and Aswal, U. (2023, January 18\u201320). Comparative Evaluation of Fraud Detection in Online Payments Using CNN-BiGRU-A Approach. Proceedings of the 2023 International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS), Erode, India."},{"key":"ref_28","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, L., and Polosukhin, I. (2017, January 4\u20139). Attention is all you need. Proceedings of the 31st International Conference on Neural Information Processing Systems, NIPS\u201917, Red Hook, NY, USA."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Cai, T., Cai, T., Yu, B., Yu, B., Xu, W., and Xu, W. (2021, January 4\u20136). Transformer-Based BiLSTM for Aspect-Level Sentiment Classification. Proceedings of the 2021 4th International Conference on Robotics, Control and Automation Engineering (RCAE), Wuhan, China.","DOI":"10.1109\/RCAE53607.2021.9638807"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Boussougou, M.K.M., and Park, D. (2023). Attention-Based 1D CNN-BiLSTM Hybrid Model Enhanced with FastText Word Embedding for Korean Voice Phishing Detection. Mathematics, 11.","DOI":"10.3390\/math11143217"},{"key":"ref_31","first-page":"486","article-title":"A New Distributed Log Anomaly Detection Method based on Message Middleware and ATT-GRU","volume":"17","author":"Fang","year":"2023","journal-title":"KSII Trans. Internet Inf. Syst."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"4548","DOI":"10.1109\/TCE.2023.3326384","article-title":"VANET Network Traffic Anomaly Detection Using GRU-Based Deep Learning Model","volume":"70","author":"ALMahadin","year":"2024","journal-title":"IEEE Trans. Consum. Electron."},{"key":"ref_33","first-page":"1172","article-title":"Opportunities in Real Time Fraud Detection: An Explainable Artificial Intelligence (XAI) Research Agenda","volume":"14","author":"Mill","year":"2023","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Nazir, Z., Kaldykhanov, D., Tolep, K.K., and Park, J.G. (2021, January 14\u201315). A Machine Learning Model Selection considering Tradeoffs between Accuracy and Interpretability. Proceedings of the 2021 13th International Conference on Information Technology and Electrical Engineering (ICITEE), Chiang Mai, Thailand.","DOI":"10.1109\/ICITEE53064.2021.9611872"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Raval, J., Bhattacharya, P., Jadav, N.K., Tanwar, S., Sharma, G., Bokoro, P.N., Elmorsy, M., Tolba, A., and Raboaca, M.S. (2023). RaKShA: A Trusted Explainable LSTM Model to Classify Fraud Patterns on Credit Card Transactions. Mathematics, 11.","DOI":"10.3390\/math11081901"},{"key":"ref_36","unstructured":"(2024, January 12). Basel Committee on Banking Supervision (BCBS). Basel II: International Convergence of Capital Measurement and Capital Standards. Available online: https:\/\/www.bis.org\/publ\/bcbs128.htm."},{"key":"ref_37","first-page":"1","article-title":"Internet Financial Credit Risk Assessment with Sliding Window and Attention Mechanism LSTM Model","volume":"30","author":"Menggang","year":"2023","journal-title":"Teh. Vjesn.\u2014Tech. Gaz."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"113467","DOI":"10.1016\/j.asoc.2025.113467","article-title":"SMOTE-ENN resampling technique with Bayesian optimization for multi-class classification of dry bean varieties","volume":"181","author":"Mukherjee","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"321","DOI":"10.1613\/jair.953","article-title":"SMOTE: Synthetic minority over-sampling technique","volume":"16","author":"Chawla","year":"2002","journal-title":"J. Artif. Intell. Res."},{"key":"ref_40","unstructured":"Baumgartner, A., Molani, S., Wei, Q., and Hadlock, J. (2022). Imputing missing observations with time sliced synthetic minority oversampling technique. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"\u00d6zt\u00fcrk, C. (2024, January 26\u201328). Enhancing Financial Time-Series Analysis with TimeGAN: A Novel Approach. Proceedings of the 2024 9th International Conference on Computer Science and Engineering (UBMK), Antalya, Turkiye.","DOI":"10.1109\/UBMK63289.2024.10773424"},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"112748","DOI":"10.1016\/j.asoc.2025.112748","article-title":"Prediction of index futures movement using TimeGAN and 3D-CNN: Empirical evidence from Korea and the United States","volume":"171","author":"Kim","year":"2025","journal-title":"Appl. Soft Comput."},{"key":"ref_43","doi-asserted-by":"crossref","first-page":"114180","DOI":"10.52202\/079017-3627","article-title":"Are self-attentions effective for time series forecasting?","volume":"37","author":"Kim","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"21800","DOI":"10.1038\/s41598-025-06885-y","article-title":"RCSAN residual enhanced channel spatial attention network for stock price forecasting","volume":"15","author":"Sun","year":"2025","journal-title":"Sci. Rep."},{"key":"ref_45","unstructured":"Ba, J.L., Kiros, J.R., and Hinton, G.E. (2016). Layer Normalization. arXiv."},{"key":"ref_46","doi-asserted-by":"crossref","first-page":"4890","DOI":"10.1038\/s41598-024-55483-x","article-title":"Advanced hybrid LSTM-transformer architecture for real-time multi-task prediction in engineering systems","volume":"14","author":"Cao","year":"2024","journal-title":"Sci. Rep."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"2673","DOI":"10.1109\/78.650093","article-title":"Bidirectional recurrent neural networks","volume":"45","author":"Schuster","year":"1997","journal-title":"IEEE Trans. Signal Process."},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Mohammed, R., Rawashdeh, J., and Abdullah, M. (2020, January 7\u20139). Machine Learning with Oversampling and Undersampling Techniques: Overview Study and Experimental Results. Proceedings of the 2020 11th International Conference on Information and Communication Systems (ICICS), Irbid, Jordan.","DOI":"10.1109\/ICICS49469.2020.239556"},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"109588","DOI":"10.1016\/j.asoc.2022.109588","article-title":"Handling class imbalance in COVID-19 chest X-ray images classification: Using SMOTE and weighted loss","volume":"129","author":"Chamseddine","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"108628","DOI":"10.1016\/j.asoc.2022.108628","article-title":"A cluster-based data splitting method for small sample and class imbalance problems in impact damage classification","volume":"120","author":"Doan","year":"2022","journal-title":"Appl. Soft Comput."},{"key":"ref_51","first-page":"1017","article-title":"Oversampling Method for Imbalanced Classification","volume":"34","author":"Zheng","year":"2015","journal-title":"Comput. Inform."},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"135","DOI":"10.1016\/j.neucom.2011.02.021","article-title":"Improved competitive learning neural networks for network intrusion and fraud detection","volume":"75","author":"Lei","year":"2012","journal-title":"Neurocomputing"},{"key":"ref_53","doi-asserted-by":"crossref","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":"Eur. J. Oper. Res."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"1981","DOI":"10.1080\/01605682.2025.2450060","article-title":"A comprehensive study on the interplay between dataset characteristics and oversampling methods","volume":"76","author":"Yang","year":"2025","journal-title":"J. Oper. Res. Soc."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"104826","DOI":"10.1016\/j.knosys.2019.06.034","article-title":"Improving interpolation-based oversampling for imbalanced data learning","volume":"187","author":"Zhu","year":"2020","journal-title":"Knowl. Based Syst."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1186\/s40537-021-00512-z","article-title":"An LSTM and GRU based trading strategy adapted to the Moroccan market","volume":"8","author":"Touzani","year":"2021","journal-title":"J. Big Data"},{"key":"ref_57","doi-asserted-by":"crossref","unstructured":"Kakkar, S., B, S., Reddy, L.S., Pal, S., Dimri, S., and Nishant, N. (2023, January 18\u201320). Analysis of Discovering Fraud in Master Card Based on Bidirectional GRU and CNN Based Model. Proceedings of the 2023 International Conference on Self Sustainable Artificial Intelligence Systems (ICSSAS), Erode, India.","DOI":"10.1109\/ICSSAS57918.2023.10331770"},{"key":"ref_58","doi-asserted-by":"crossref","first-page":"e1872","DOI":"10.7717\/peerj-cs.1872","article-title":"RNN-BiLSTM-CRF based amalgamated deep learning model for electricity theft detection to secure smart grids","volume":"10","author":"Khalid","year":"2024","journal-title":"PeerJ Comput. Sci."}],"container-title":["Information"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/1\/5\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T14:40:39Z","timestamp":1766500839000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2078-2489\/17\/1\/5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,21]]},"references-count":58,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["info17010005"],"URL":"https:\/\/doi.org\/10.3390\/info17010005","relation":{},"ISSN":["2078-2489"],"issn-type":[{"value":"2078-2489","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,12,21]]}}}