Analisis Efektivitas Algoritma Pembelajaran Mesin dalam Deteksi Penipuan Transaksi Online
Bilah Samping Artikel
Isi Artikel Utama
Abstrak
Penipuan transaksi online merupakan ancaman serius dengan dampak finansial yang signifikan. Penelitian ini menganalisis efektivitas dua algoritma pembelajaran mesin, yaitu Random Forest (RF) dan Neural Networks (NN), dalam mendeteksi transaksi penipuan. Dataset yang digunakan terdiri dari 100.000 transaksi (10% di antaranya fraud) dari TranSecure Database 2023. Hasil eksperimen menunjukkan bahwa NN mencapai kinerja terbaik dengan akurasi 95%, presisi 0.93, dan recall 0.90, sedangkan RF menghasilkan akurasi 93%, presisi 0.91, dan recall 0.89. Tantangan utama meliputi kebutuhan data berkualitas tinggi dan adaptasi terhadap pola penipuan yang dinamis. Temuan ini membuktikan bahwa NN lebih unggul dalam menangani pola kompleks, meskipun memerlukan sumber daya komputasi lebih besar. Penelitian ini memberikan kontribusi praktis dalam pengembangan sistem deteksi penipuan yang lebih robust di industri keuangan digital.
Rincian Artikel
Referensi
Z. Zhang, J. Li, C. Liu, and X. Wang, "Random Forest Algorithm for Fraud Detection," Journal of Machine Learning Research, vol. 15, no. 3, pp. 456-470, 2020.
J. Smith and K. Lee, "Neural Networks in Fraud Detection," International Journal of Data Science, vol. 7, no. 2, pp. 234-245, 2021.
J. Wang, S. Chen, and H. Zhang, "Comparative Analysis of Machine Learning Algorithms for Financial Fraud Detection," IEEE Transactions on Knowledge and Data Engineering, vol. 34, no. 5, pp. 2178-2190, 2022.
M. Liu and R. Zhao, "Random Forest Applications in E-commerce Fraud Detection," Journal of Cybersecurity, vol. 5, no. 1, pp. 78-92, 2023.
A. Prakash, B. Singh, and C. Kumar, "Attention-Based Neural Networks for Digital Payment Fraud Detection," International Journal of Information Security, vol. 23, no. 1, pp. 112-125, 2024.
Y. Kang and S. Kwon, "Ensemble Learning Approaches for Robust Fraud Detection Systems," ACM Transactions on Intelligent Systems and Technology, vol. 14, no. 3, pp. 1-20, 2023.
R. Brown, T. Johnson, and P. Garcia, "Machine Learning for Anomaly Detection in Financial Transactions," Journal of Financial Technology, vol. 8, no. 2, pp. 145-160, 2020.
V. Kumar, A. Sharma, M. Singh, K. Bhardwaj, and G. Gupta, "Detecting Credit Card Fraud by Decision Trees and Support Vector Machines," Journal of Intelligent Systems, vol. 29, no. 1, pp. 1440-1451, 2020.
L. Patel and S. Gupta, "An Optimal Approach for Fraud Detection by SVM and Deep Learning," AIP Conference Proceedings, vol. 2821, no. 1, 070028, 2022.
G. Jones and D. Miller, "KNN-based Fraud Detection: Challenges and Opportunities," International Journal of Computer Science and Information Security, vol. 17, no. 6, pp. 89-101, 2019.
P. Kumar, M. Thapa, and S. Bhattacharya, "Finance Fraud Detection With Neural Network," International Journal of Advanced Research in Computer Science, vol. 11, no. 6, pp. 34-41, 2020.
Statista, "Online Fraud Statistics," 2023. [Online]. Available: https://www.statista.com/statistics/online-fraud
https://jurnal.polgan.ac.id/index.php/jmp/article/view/14186
https://onlinelibrary.wiley.com/doi/10.1155/2023/8134627
https://www.researchgate.net/publication/347411268_Finance_Fraud_Detection_With_Neural_Network