Deep Support Vector Data Description for Anomaly Detection in Credit Insurance Claim Processes
Indonesian Journal of Artificial Intelligence and Data Mining · 06.11.2025 · 8 (3) · 646-656
DOI: 10.24014/ijaidm.v8i3.38134 ↗Kurz gefasst
Fachartikel in der Zeitschrift Indonesian Journal of Artificial Intelligence and Data Mining, online erschienen am 06.11.2025. Verfasst von Sari Ramadhana und 2 weiteren Autor:innen. Die Arbeit nennt 46 Literaturangaben.
Abstract (Originalsprache)
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.
Zitieren
APA
Ramadhana, S., Nababan, E. B., & Sitompul, O. S. (2025). Deep Support Vector Data Description for Anomaly Detection in Credit Insurance Claim Processes. Indonesian Journal of Artificial Intelligence and Data Mining, 8(3), 646-656. https://doi.org/10.24014/ijaidm.v8i3.38134
Vancouver
Ramadhana S, Nababan EB, Sitompul OS. Deep Support Vector Data Description for Anomaly Detection in Credit Insurance Claim Processes. Indonesian Journal of Artificial Intelligence and Data Mining. 2025;8(3):646-656. doi:10.24014/ijaidm.v8i3.38134
BibTeX
@article{Ramadhana2025,
author = {Ramadhana, Sari and Nababan, Erna Budhiarti and Sitompul, Opim Salim},
title = {Deep Support Vector Data Description for Anomaly Detection in Credit Insurance Claim Processes},
journal = {Indonesian Journal of Artificial Intelligence and Data Mining},
year = {2025},
volume = {8},
number = {3},
pages = {646--656},
doi = {10.24014/ijaidm.v8i3.38134}
}
EUVIMED