Hybrid Fraud Detection for Government Financial Transactions Using Deep Isolation Forest and Extreme Gradient Boosting: A Case Study from an Indonesian Government Institution
DOI:
https://doi.org/10.61194/ijtc.v7i3.2600Keywords:
anomaly detection, deep isolation forest, XGBoost, fraud detection, government financial transactionsAbstract
Ensuring fraud-free financial management through the investigation of anomalous transactions is essential for promoting transparency and integrity in government institutions. However, existing approaches often treat anomaly detection and fraud classification as separate tasks and frequently assume that all anomalies indicate fraud. This study proposes a two-stage computational fraud detection framework that integrates Deep Isolation Forest (DIF) for anomaly detection and Extreme Gradient Boosting (XGBoost) for fraud classification, with an intermediate expert validation process. The framework was applied to a dataset of 9,166 expenditure transactions from an Indonesian government institution, consisting of 894 fraudulent and 8,272 non-fraudulent records. First, DIF identifies transactions with anomalous patterns. Subsequently, three certified internal auditors with more than ten years of experience at the Ministry of Finance review the detected anomalies to determine whether they genuinely indicate fraud. The validated results are then incorporated into an enriched dataset combining original transaction attributes and anomaly-derived features, which is used to train the XGBoost classifier. Expert judgement functions as a validation mechanism that improves label reliability and reduces the risk of misclassifying anomalies as fraud. Evaluation on a held-out test set of 1,834 transactions demonstrates strong predictive performance, achieving an accuracy of 0.9984, precision of 0.98, recall of 1.00, and an F1-score of 0.99. Although the findings are limited to a single institutional environment and require validation across multiple government agencies, the proposed framework demonstrates that integrating expert interpretation between anomaly detection and fraud classification enhances fraud identification and provides a practical, auditor-aligned approach to public-sector financial oversight.
References
Law Number 1 of 2004 Concerning State Treasury, Pub. L. 1 (2004). https://peraturan.bpk.go.id/
Ali, A. Al, Khedr, A. M., El-Bannany, M., & Kanakkayil, S. (2023). A Powerful Predicting Model for Financial Statement Fraud Based on Optimized XGBoost Ensemble Learning Technique. Applied Sciences (Switzerland), 13(4). https://doi.org/10.3390/app13042272
Andriyanto, R., & Januarti, I. (2026). Implementing Artificial Intelligence in Auditing: A Systematic Literature Review of Trends, Challenges, and Adoption. Owner, 10(2), 1925–1937. https://doi.org/10.33395/owner.v10i2.3389
Bakumenko, A., & Elragal, A. (2022). Detecting Anomalies in Financial Data Using Machine Learning Algorithms. Systems, 10(5). https://doi.org/10.3390/systems10050130
Carcillo, F., Le Borgne, Y. A., Caelen, O., Kessaci, Y., Oblé, F., & Bontempi, G. (2021). Combining unsupervised and supervised learning in credit card fraud detection. Information Sciences, 557(May), 317–331. https://doi.org/10.1016/j.ins.2019.05.042
Carletti, M., Terzi, M., & Susto, G. A. (2023). Interpretable Anomaly Detection with DIFFI: Depth-based feature importance of Isolation Forest. Engineering Applications of Artificial Intelligence, 119. https://doi.org/10.1016/j.engappai.2022.105730
Chen, T., & Guestrin, C. (2016). XGBoost: A Scalable Tree Boosting System. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 785–794. https://doi.org/10.1145/2939672.2939785
Dhieb, N., Ghazzai, H., Besbes, H., & Massoud, Y. (2019). Extreme gradient boosting machine learning algorithm for safe auto insurance operations. 2019 IEEE International Conference on Vehicular Electronics and Safety, ICVES 2019, (September). https://doi.org/10.1109/ICVES.2019.8906396
Faccia, A. (2026). Explainable AI (XAI) in Auditing: Bridging the Gap Between Predictive Fraud Models and Regulatory Standards. Journal of Risk and Financial Management, 19(5). https://doi.org/10.3390/jrfm19050311
Guan, H., Li, S., Wang, Q., Lyulyov, O., & Pimonenko, T. (2022). Financial Fraud Identification of the Companies Based on the Logistic Regression Model. Journal of Competitiveness, 14(4), 155–171. https://doi.org/10.7441/joc.2022.04.09
Hajek, P., Abedin, M. Z., & Sivarajah, U. (2023). Fraud Detection in Mobile Payment Systems using an XGBoost-based Framework. Information Systems Frontiers, 25(5), 1985–2003. https://doi.org/10.1007/s10796-022-10346-6
Hasibuan, A. A., Irsan Nasution, M., & Nasution, M. I. (2026). id 2 2nd International Conference on Islamic Community Studies (ICICS) Theme: History of Malay Civilisation and Islamic Human Capacity and Halal Hub in the Globalization Era The Impact of Real-Time and Continuous Auditing on Financial Transparency and Fraud Detection: A Systematic Literature Review. https://proceeding.pancabudi.ac.id/index.php/ICIE/index
Indonesian Institute of Certified Public Accountants (IAPI). (2021). SA 240 (Revised 2021): The Auditor’s Responsibilities Relating to Fraud in an Audit of Financial Statements. https://iapi.or.id/
Minister of Finance Regulation Number 62/PMK.01/2023 Concerning Budget Planning, Budget Implementation, Accounting and Financial Reporting, Pub. L. 62/PMK.01/2023 (2023). https://jdih.kemenkeu.go.id/
Li, X. (2023). Financial Fraud: Identifying Corporate Tax Report Fraud Under the Xgboost Algorithm. EAI Endorsed Transactions on Scalable Information Systems, 10(4), 1–7. https://doi.org/10.4108/eetsis.v10i3.3033
Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008). Isolation Forest. 2008 Eighth IEEE International Conference on Data Mining, 413–422. https://doi.org/10.1109/ICDM.2008.17
Milka Wijayanti Sunarto, Dendy Kurniawan, Edy Siswanto, & Haris Ihsanil Huda. (2023). Deteksi Anomali Menggunakan Extended Isolation Forest (Eif). Teknik: Jurnal Ilmu Teknik Dan Informatika, 1(2), 96–111. https://doi.org/10.51903/teknik.v1i2.324
Moomtaheen, F., Bagui, S. S., Bagui, S. C., & Mink, D. (2024). Extended Isolation Forest for Intrusion Detection in Zeek Data. Information (Switzerland), 15(7). https://doi.org/10.3390/info15070404
Government Regulation Number 60 of 2008 Concerning Government Internal Control System (2008). https://peraturan.bpk.go.id/
Said Mirza Pahlevi. (2024). Kecerdasan Buatan dengan Deep Learning (Vol. 1). Elex Media Komputindo.
Saifudin, S., Januarti, I., & Purwanto, A. (2025). The Role of Artificial Intelligence in the Audit Process and How to Fraud Detections: A Literature Outlook. Journal of Ecohumanism, 4(1), 4185–4203. https://doi.org/10.62754/joe.v4i1.6301
Sodnomdavaa, T., & Lkhagvadorj, G. (2026). Financial Statement Fraud Detection Through an Integrated Machine Learning and Explainable AI Framework. Journal of Risk and Financial Management, 19(1), 13. https://doi.org/10.3390/jrfm19010013
Sopiyan, M., Fauziah, F., & Wijaya, Y. F. (2022). Fraud Detection Using Random Forest Classifier, Logistic Regression, and Gradient Boosting Classifier Algorithms on Credit Cards. JUITA: Jurnal Informatika, 10(1), 77. https://doi.org/10.30595/juita.v10i1.12050
Suci Azzahra. (2025). The Use of Artificial Intelligence (Al) in Fraud Detection by Government Auditors: A Systematic Literature Review. International Conference Proceedings Universitas Islam Blitar, (1).
Taha, A. A., & Malebary, S. J. (2020). An Intelligent Approach to Credit Card Fraud Detection Using an Optimized Light Gradient Boosting Machine. IEEE Access, 8, 25579–25587. https://doi.org/10.1109/ACCESS.2020.2971354
Thanathamathee, P., Sawangarreerak, S., Chantamunee, S., & Nizam, D. N. M. (2024). SHAP-Instance Weighted and Anchor Explainable AI: Enhancing XGBoost for Financial Fraud Detection. Emerging Science Journal, 8(6), 2404–2430. https://doi.org/10.28991/ESJ-2024-08-06-016
Wana, D., & Rohman, A. (2025). Fraud Detection in Government in the Last Ten Years. In Journal of Applied Accounting and Taxation Article History (Vol. 10, Number 1).
Wang, L. (2024). Financial Fraud Identification Model of Listed Companies based on Time-Series Information. WSEAS Transactions on Computer Research, 12, 211–223. https://doi.org/10.37394/232018.2024.12.21
Wibowo, S. R., & Wibowo, A. (2025). Continous Auditing and Explainable AI for Enhancing Real Time Financial Analysis. Jurnal Akuntansi Dan Bisnis, 5(2), 10–19. https://doi.org/10.51903/jiab.v5i2.931
Xiang, H., Hu, H., & Zhang, X. (2022). DeepiForest: A Deep Anomaly Detection Framework with Hashing Based Isolation Forest. Proceedings - IEEE International Conference on Data Mining, ICDM, 2022-Novem(Icdm), 1251–1256. https://doi.org/10.1109/ICDM54844.2022.00163
Xu, H., Pang, G., Wang, Y., & Wang, Y. (2023). Deep Isolation Forest for Anomaly Detection. IEEE Transactions on Knowledge and Data Engineering, 35(12), 12591–12604. https://doi.org/10.1109/TKDE.2023.3270293
Zulfikar, A., Rahmani, Fa. A., & Azizah, N. (2023). Deteksi Anomali Menggunakan Isolation Forest Belanja Barang Persediaan Konsumsi Pada Satuan Kerja Kepolisian Republik Indonesia. Jurnal Manajemen Perbendaharaan, 4(1), 1–15. https://doi.org/10.33105/jmp.v4i1.435
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Ni Komang Yossy Trisna Sukawati Sukawati, Rojali
This work is licensed under a Creative Commons Attribution 4.0 International License.
This work is licensed under a Creative Commons Attribution 4.0 International License.
