Implementasi XGBoost dan SMOTE untuk Meningkatkan Deteksi Transaksi Fraud di Industri Jasa Keuangan
DOI:
https://doi.org/10.52436/1.jpti.518Kata Kunci:
bpr, deteksi fraud, machine learning, smote, transaksi , keuangan, xgboostAbstrak
Tindakan fraud (fraud) di industri jasa keuangan, khususnya pada Bank Perekonomian Rakyat (BPR), menjadi tantangan serius yang memengaruhi stabilitas keuangan, kepercayaan nasabah, dan perekonomian nasional. Masalah ini semakin sulit terdeteksi dengan berkembangnya teknologi yang mempermudah pelaku melakukan manipulasi laporan keuangan dan penggelapan dana. Penelitian ini bertujuan untuk mengembangkan model deteksi fraud berbasis algoritma XGBoost yang dipadukan dengan teknik SMOTE (Synthetic Minority Over-sampling Technique) untuk mengatasi ketidakseimbangan data. Melalui analisis terhadap data transaksi keuangan BPR, model ini menunjukkan kemampuan yang tinggi dalam mendeteksi transaksi mencurigakan. Hasil penelitian menunjukkan bahwa model XGBoost dapat meningkatkan akurasi deteksi fraud hingga 96%, dengan nilai Area Under the Curve (AUC) yang signifikan. Pendekatan ini tidak hanya efektif dalam mendeteksi transaksi mencurigakan, tetapi juga memberikan kontribusi dalam memperkuat sistem pengendalian internal dan menerapkan prinsip tata kelola perusahaan yang baik (good corporate governance). Penelitian ini memberikan solusi inovatif dalam pencegahan fraud di BPR dan berperan penting bagi pengembangan ilmu pengetahuan di bidang data sains serta praktik industri. Diharapkan, hasil penelitian ini dapat menjadi panduan strategis bagi manajemen BPR dalam merancang sistem deteksi fraud yang lebih efektif, sehingga meningkatkan kepercayaan masyarakat terhadap institusi keuangan.
Unduhan
Referensi
A. Q. Abdulghani, O. N. UCAN, and K. M. A. Alheeti, “Credit Card Fraud Detection Using XGBoost Algorithm,” in 2021 14th International Conference on Developments in eSystems Engineering (DeSE), Dec. 2021, pp. 487–492. doi: 10.1109/DeSE54285.2021.9719580.
U. Detthamrong, W. Chansanam, T. Boongoen, and N. Iam-On, “Enhancing Fraud Detection in Banking using Advanced Machine Learning Techniques,” International Journal of Economics and Financial Issues, vol. 14, no. 5, pp. 177–184, Sep. 2024, doi: 10.32479/ijefi.16613.
T. R. Noviandy, G. M. Idroes, A. Maulana, I. Hardi, E. S. Ringga, and R. Idroes, “Credit Card Fraud Detection for Contemporary Financial Management Using XGBoost-Driven Machine Learning and Data Augmentation Techniques,” Indatu Journal of Management and Accounting, vol. 1, no. 1, pp. 29–35, Sep. 2023, doi: 10.60084/ijma.v1i1.78.
P. Gupta, S. Shukla, V. Kikan, and A. Kumar, “Enhancing Fraud Detection in Credit Card Transactions using XGBoost and SMOTE: A Comparative Study,” in 2024 IEEE International Conference on Smart Power Control and Renewable Energy (ICSPCRE), 2024, pp. 1–6. doi: 10.1109/ICSPCRE62303.2024.10675080.
K. Garg, K. S. Gill, S. Malhotra, S. Devliyal, and G. Sunil, “Implementing the XGBOOST Classifier for Bankruptcy Detection and Smote Analysis for Balancing Its Data,” in 2024 2nd International Conference on Computer, Communication and Control (IC4), 2024, pp. 1–5. doi: 10.1109/IC457434.2024.10486274.
S. MP, M. Pandey, Garima, J. V, V. B. Maral, and S. Das, “Investigating the Use of Data Mining for Knowledge Discovery,” in 2023 3rd International Conference on Smart Generation Computing, Communication and Networking (SMART GENCON), 2023, pp. 1–7. doi: 10.1109/SMARTGENCON60755.2023.10442608.
Y. Sei, J. A. Onesimu, and A. Ohsuga, “Machine Learning Model Generation With Copula-Based Synthetic Dataset for Local Differentially Private Numerical Data,” IEEE Access, vol. 10, pp. 101656–101671, 2022, doi: 10.1109/ACCESS.2022.3208715.
E. H. Yulianti, O. Soesanto, and Y. Sukmawaty, “Penerapan Metode Extreme Gradient Boosting (XGBOOST) pada Klasifikasi Nasabah Kartu Kredit,” JOMTA Journal of Mathematics: Theory and Applications, vol. 4, no. 1, 2022.
A. K. Saw, P. Luthra, and D. Thakur, “Optimizing Credit Card Fraud Detection: Random Forest and XGBoost Ensemble,” in 2024 International Conference on Advances in Computing Research on Science Engineering and Technology (ACROSET), 2024, pp. 1–6. doi: 10.1109/ACROSET62108.2024.10743811.
S. Li and X. Zhang, “Research on orthopedic auxiliary classification and prediction model based on XGBoost algorithm,” Neural Comput Appl, vol. 32, Apr. 2020, doi: 10.1007/s00521-019-04378-4.
I. Hanif, “Implementing Extreme Gradient Boosting (XGBoost) Classifier to Improve Customer Churn Prediction,” European Alliance for Innovation n.o., Jan. 2020. doi: 10.4108/eai.2-8-2019.2290338.
H. Xia, W. An, and Zuopeng (Justin) Zhang, “Credit Risk Models for Financial Fraud Detection,” Journal of Database Management, vol. 34, no. 1, pp. 1–20, Apr. 2023, doi: 10.4018/jdm.321739.
A. A. Saputra, B. N. Sari, C. Rozikin, U. Singaperbangsa, and K. Abstrak, “Penerapan Algoritma Extreme Gradient Boosting (Xgboost) Untuk Analisis Risiko Kredit,” Jurnal Ilmiah Wahana Pendidikan, vol. 10, no. 7, pp. 27–36, 2024, doi: 10.5281/zenodo.10960080.
S. T. Mhlanga and M. Lall, “Influence of Normalization Techniques on Multi-criteria Decision-making Methods,” J Phys Conf Ser, vol. 2224, no. 1, p. 12076, Apr. 2022, doi: 10.1088/1742-6596/2224/1/012076.
H. G. W. Ansari and Dr. M. D. Patil, “Enhancing Credit Card Fraud Detection Using P-XGBoost: A Comparative Study Classical Machine Learning Techniques,” Int J Res Appl Sci Eng Technol, vol. 11, no. 9, pp. 618–623, Sep. 2023, doi: 10.22214/ijraset.2023.55698.
Q. Zhang, “Financial Data Anomaly Detection Method Based on Decision Tree and Random Forest Algorithm,” Journal of Mathematics, vol. 2022, pp. 1–10, Apr. 2022, doi: 10.1155/2022/9135117.
A. Al Ali, A. M. Khedr, M. El-Bannany, and S. Kanakkayil, “A Powerful Predicting Model for Financial Statement Fraud Based on Optimized XGBoost Ensemble Learning Technique,” Applied Sciences (Switzerland), vol. 13, no. 4, Feb. 2023, doi: 10.3390/app13042272.
X. Li, “Financial Fraud: Identifying Corporate Tax Report Fraud Under the Xgboost Algorithm,” EAI Endorsed Transactions on Scalable Information Systems, vol. 10, no. 4, pp. 1–7, 2023, doi: 10.4108/eetsis.v10i3.3033.
