ADDITIONAL MENU
Deep Support Vector Data Description for Anomaly Detection in Credit Insurance Claim Processes
Abstract
This study evaluates Deep Support Vector Data Description (Deep-SVDD) for anomaly detection in credit insurance claim submissions processed through host-to-host systems. The model addresses irregularities such as duplicate claims, inconsistent values, and delayed reporting by learning normal claim behavior in a latent space and applying calibrated thresholds. Using a dataset of 5,000 claims with mixed-type variables, Deep-SVDD achieved strong performance on the validation set, with high precision, recall, and ROC-AUC. Confusion matrix and Recall@K analyses confirmed low false alarms and effective anomaly ranking, capturing a substantial portion of anomalies among top-ranked claims. These results demonstrate Deep-SVDD’s potential as a scalable and efficient early detection layer, improving transparency and reliability in credit insurance claim verification.
Keywords
Anomaly Detection; Credit Insurance; Deep-SVDD; Machine Learning; ROC-AUC
Full Text:
PDFReferences
Singh, P., Singla, K., Piyush, P., Chugh, B., 2024. Anomaly Detection Classifiers for Detecting Credit Card Fraudulent Transactions. IEEE, pp. 1–6. https://doi.org/10.1109/ICAECT60202.2024.10469194
Lieus, H.J., Tedja, D., Joewita, V., Hidayat, A.S.E., Silalahi, A.R.J., 2023. Application Of Expected Credit Loss Model And Markov Chain To Calculate Net Single Premium Of Unsecured Credit Insurance. Barekeng J. Ilmu Mat. Dan Terap. 17, 2161–2170. https://doi.org/10.30598/barekengvol17iss4pp2161-2170
Debora, Sirait, N., Sunarmi, & Siregar (2021). Mitigation of default risk through insurance in Peer-to-Peer Lending Financial Technology. EAI Endorsed Transactions on Scalable Information Systems, 8(29), Article e4. DOI: 10.4108/eai.29-6-2021.2312604
IMARC Group. (2024, December 19). Global trade credit insurance market report by component, coverages, enterprise size, application, industry vertical, and region 2025–2033. IMARC Group. https://www.imarcgroup.com/global-trade-credit-insurance-market
Singireddy, S., 2023. Integrating Deep Learning and Machine Learning Algorithms in Insurance Claims Processing: A Study on Enhancing Accuracy, Speed, and Fraud Detection for Policyholders. Educ. Adm. Theory Pract. https://doi.org/10.53555/kuey.v29i4.9668
Annaboina,. Krishna, Prasoona, S., Ashritha, C., Reddy, P.C., 2025. Fraud Detection in Medical Insurance Claim Systems using Machine Learning. INTERANTIONAL J. Sci. Res. Eng. Manag. 09, 1–9. https://doi.org/10.55041/IJSREM40522
Rao, N., Krishnasubramaniam, V., Waghamale, S., Sondur, S., Ansari, A., Iyer, S., Singh, A., & Vijayalakshmi, M. (2023). Data Validation for Eligibility Criteria and Death Benefit Claims for Insurance Policies. 2023 4th International Conference for Emerging Technology (INCET), 1–7. IEEE. https://doi.org/10.1109/INCET57972.2023.10170530
Nortey, E. N. N., Pometsey, R., Asiedu, L., Iddi, S., & Mettle, F. (2021). Anomaly Detection in Health Insurance Claims Using Bayesian Quantile Regression. International Journal of Mathematics and Mathematical Sciences, 2021, 1–11. https://doi.org/10.1155/2021/6667671
Sharifi Garmdareh, M., Soleimani Neysiani, B., Zahiri Nogorani, M., & Bahramizadegan, M. (2023). A Machine Learning-based Approach for Medical Insurance Anomaly Detection by Predicting Indirect Outpatients’ Claim Price. 2023 9th International Conference on Web Research (ICWR), 129–134. IEEE. https://doi.org/10.1109/ICWR57742.2023.10139290
ResearchAndMarkets.com. (2023, March 17). Global trade credit insurance market report 2022 to 2030: Rapid digitization of the insurance sector drives growth. GlobeNewswire. https://www.globenewswire.com/news-release/2023/03/17/2629575/28124/en/Global-Trade-Credit-Insurance-Market-Report-2022-to-2030-Rapid-Digitization-of-the-Insurance-Sector-Drives-Growth.html
Kemp, J., Barker, C., Good, N., Bain, M., 2022. Sequential pattern detection for identifying courses of treatment and anomalous claim behaviour in medical insurance. IEEE, pp. 3039–3046. https://doi.org/10.1109/BIBM55620.2022.9995541
Hamid, Z., Khalique, F., Mahmood, S., Daud, A., Bukhari, A., Alshemaimri, B., 2024. Healthcare insurance fraud detection using data mining. BMC Med. Inform. Decis. Mak. 24, 112. https://doi.org/10.1186/s12911-024-02512-4
Yu, J., Yang, X., & Zhao, J. (2023). Detecting Anomalies in Health Insurance Claim Data with Unsupervised Machine Learning. IEEE Access, 11, 76601–76612. https://doi.org/10.1109/ACCESS.2023.3291234
Wang, H., Zhang, Y., & Li, P. (2022). Fraud detection in health insurance claims using deep learning techniques. Applied Intelligence, 52(6), 5678–5693. https://doi.org/10.1007/s10489-021-02821-4
Singh, A., Gupta, R., & Kumar, N. (2021). Big data analytics in insurance: Transforming fraud detection and risk assessment. Journal of Big Data, 8(1), 114. https://doi.org/10.1186/s40537-021-00520-7
Fan, Z., Luangsodsai, A., Sinapiromsaran, K., 2024. Mass-Ratio-Average-Absolute-Deviation Based Outlier Factor for Anomaly Scoring. IEEE, pp. 488–493. https://doi.org/10.1109/JCSSE61278.2024.10613697
Fan, Z., Kaitian, L., Ziyi, C., Jing, Y., 2022. Intelligent forecasting electric vehicle purchase model based on logistic and multi-objective optimization model. IEEE, pp. 752–758. https://doi.org/10.1109/ICPECA53709.2022.9718832
I. I., H., M., A., U. F., S., K. I., B., D., A., N. H., D., 2024. Evaluating the Performances of Robust Logistic Regression Models in the Presence of Outliers. Afr. J. Math. Stat. Stud. 7, 320–327. https://doi.org/10.52589/AJMSS-YKDFCYQS
Mardiansyah, H., Suwilo, S., Nababan, E. B., & Efendi, S. (2024). The role of Louvain-coloring clustering in the detection of fraud transactions. International Journal of Electrical and Computer Engineering (IJECE), 14(1), 608–616. https://doi.org/10.11591/ijece.v14i1.pp608-616
Zaldi, M. A. A., Sitompul, O. S., Nababan, E. B., & Crispin, A. R. (2024). Twitter data extraction for food and beverage business analytics. In Proceedings of the 2nd International Conference on Technology Innovation and Its Applications (ICTIIA). IEEE. https://doi.org/10.1109/ICTIIA61827.2024.10761920.
López, D., Aguilera-Martos, I., García-Bárzana, M., Herrera, F., García-Gil, D., & Luengo, J. (2023). Fusing anomaly detection with false positive mitigation methodology for predictive maintenance under multivariate time series. Information Fusion, 100, 101957. https://doi.org/10.1016/j.inffus.2023.101957
Qiu, J., Shi, H., Hu, Y., & Yu, Z. (2023). Unraveling false positives in unsupervised defect detection models: A study on anomaly-free training datasets. Sensors, 23(23), 9360. https://doi.org/10.3390/s23239360
Al Jallad, K., Aljnidi, M., & Desouki, M. S. (2020). Anomaly detection optimization using big data and deep learning to reduce false-positive. Journal of Big Data, 7, 1–12. https://doi.org/10.1186/s40537-020-00346-1
Tax, D., & Duin, R. (2004). Support Vector Data Description. Machine Learning, 54, 45-66. https://doi.org/10.1023/B:MACH.0000008084.60811.49.
Ruff, L., Vandermeulen, R. A., Görnitz, N., Deecke, L., Siddiqui, S. A., Binder, A., Müller, E., & Kloft, M. (2018). Deep one-class classification. In Proceedings of the 35th International Conference on Machine Learning (Vol. 80, pp. 4393–4402). PMLR.
Anomaly Detection, in: Pascal, P., Ienco, D. (Eds.), Discovery Science, Lecture Notes in Computer Science. Springer Nature Switzerland, Cham, pp. 318–328. https://doi.org/10.1007/978-3-031-18840-4_23
Huang, W., Li, Y., Xu, Z., Yao, X., Wan, R., 2024. Improved Deep Support Vector Data Description Model Using Feature Patching for Industrial Anomaly Detection. Sensors 25, 67. https://doi.org/10.3390/s25010067
Jiang, R., Yang, Z., Zhao, J., 2023. A Complete Deep Support Vector Data Description for One Class Learning. IEEE Access 11, 117494–117507. https://doi.org/10.1109/ACCESS.2023.3325734
Azim, E., Wang, D., Fu, Y., 2023. Deep Graph Stream SVDD: Anomaly Detection in Cyber-Physical Systems. https://doi.org/10.48550/ARXIV.2302.12918
Wen, L., Gao, L., Li, X., & Zhang, Y. (2023). Deep anomaly detection for high-dimensional insurance claim data using support vector data description networks. Expert Systems with Applications, 233, 120929. https://doi.org/10.1016/j.eswa.2023.120929
Sokolova, M., Japkowicz, N., & Szpakowicz, S. (2022). Automation in insurance fraud detection: Reducing manual workload with deep learning models. Decision Support Systems, 160, 113750. https://doi.org/10.1016/j.dss.2022.113750
Zhang, H., Liu, Q., & Zhao, W. (2021). Efficient anomaly detection in financial claims processing using deep one-class classification models. Knowledge-Based Systems, 229, 107331. https://doi.org/10.1016/j.knosys.2021.107331
Hankede, M., & Mwelwa, A. (2024). Assessing the factors causing delay by insurance companies to pay claims to customers: A case of selected Insurance Companies, and Pensions and Insurance Authority (PIA). East African Finance Journal, 3(2). https://doi.org/10.59413/eafj/v3.i2.8
Kumar, R., Singh, P., & Sharma, S. (2023). Anomaly detection in delayed insurance claim submissions using machine learning. Journal of Financial Crime, 30(4), 1123–1138. https://doi.org/10.1108/JFC-05-2022-0099
Chen, Y., Wu, L., & Zhang, H. (2022). Detecting irregular claim filing patterns in health insurance using temporal anomaly detection. Expert Systems with Applications, 198, 116804. https://doi.org/10.1016/j.eswa.2022.116804
Alghamdi, R., & Mehmood, R. (2021). Applications of big data analytics in health insurance systems: A study on fraud detection and anomaly in claim submissions. Computers in Biology and Medicine, 140, 105095. https://doi.org/10.1016/j.compbiomed.2021.105095
Patel, R., & Desai, M. (2023). Machine learning for anomaly detection in delayed insurance claims. Journal of Financial Services Analytics, 9(2), 145–162. https://doi.org/10.1080/27693236.2023.1122334
Huang, Y., Chen, X., & Zhao, L. (2021). Temporal patterns in fraudulent insurance claims: Detecting delays and irregularities using deep learning models. Information Sciences, 570, 345–359. https://doi.org/10.1016/j.ins.2021.04.015
Rahman, M., & Sultana, T. (2020). Anomaly detection in health insurance claims with a focus on late submissions. Health Informatics Journal, 26(4), 2762–2778. https://doi.org/10.1177/1460458220944551
Harrou, F., Sun, Y., Hering, A., Madakyaru, M., & Dairi, A. (2021). Unsupervised deep learning-based process monitoring methods. In Data Analytics and Applications (pp. 193–223). Elsevier. https://doi.org/10.1016/b978-0-12-819365-5.00012-7
Ahn, J., & Kim, G. (2022). Application of optimal clustering and metric learning to patch-based anomaly detection. Pattern Recognition Letters, 154, 110–115. https://doi.org/10.1016/j.patrec.2022.01.017
Zhou, Y., Liang, X., Zhang, W., Zhang, L., & Song, X. (2021). VAE-based Deep SVDD for anomaly detection. Neurocomputing, 453, 131–140. https://doi.org/10.1016/j.neucom.2021.04.089
Liu, C., & Gryllias, K. (2021). A Deep Support Vector Data Description Method for Anomaly Detection in Helicopters. Prognostics and Health Management Conference, 6(1), 9. https://doi.org/10.36001/PHME.2021.V6I1.2957
Noji, Y., Kimura, T., & Cheng, J. (2023). Anomaly Web Page Detection Using HDBSCAN and Deep SVDD. 2023 International Conference on Consumer Electronics - Taiwan (ICCE-Taiwan), 465–466. https://doi.org/10.1109/ICCE-Taiwan58799.2023.10226803
Jia, Y., Cheng, J., Liu, H., & Hou, J. (2024). Towards Calibrated Deep Clustering Network. ArXiv preprint arXiv:2403.02998. https://doi.org/10.48550/arXiv.2403.02998
Joeres, R., Blumenthal, D.B., Kalinina, O.V., 2025. Data splitting to avoid information leakage with DataSAIL. Nat. Commun. 16, 3337. https://doi.org/10.1038/s41467-025-58606-8
DOI: http://dx.doi.org/10.24014/ijaidm.v8i3.38134
Refbacks
- There are currently no refbacks.
Office and Secretariat:
Big Data Research Centre
Puzzle Research Data Technology (Predatech)
Laboratory Building 1st Floor of Faculty of Science and Technology
UIN Sultan Syarif Kasim Riau
Jl. HR. Soebrantas KM. 18.5 No. 155 Pekanbaru Riau – 28293
Website: http://predatech.uin-suska.ac.id/ijaidm
Email: ijaidm@uin-suska.ac.id
e-Journal: http://ejournal.uin-suska.ac.id/index.php/ijaidm
Phone: 085275359942
Journal Indexing:
Google Scholar | ROAD | PKP Index | BASE | ESJI | General Impact Factor | Garuda | Moraref | One Search | Cite Factor | Crossref | WorldCat | Neliti | SINTA | Dimensions | ICI Index Copernicus
IJAIDM Stats