Deteksi Anomali dalam Penipuan E-commerce Menggunakan Hybrid Autoencoder-Transformer Frameworks
DOI:
https://doi.org/10.26418/jp.v11i1.82330Keywords:
Deteksi Anomali, Penipuan E-Commerce, Hybrid Auto Encoder, Transformer, Deep LearningAbstract
Peningkatan e-commerce telah menyebabkan peningkatan aktivitas penipuan, seperti pencurian identitas dan transaksi palsu, yang menimbulkan risiko signifikan terhadap keamanan transaksi online. Penelitian ini mengusulkan kerangka kerja hybrid yang menggabungkan Autoencoder (AE) untuk reduksi dimensi dan representasi laten data, serta Transformer untuk menangkap ketergantungan global dan lokal melalui mekanisme self-attention. Pendekatan ini dirancang untuk mengatasi keterbatasan metode tradisional dalam mendeteksi pola data kompleks dan meningkatkan kinerja deteksi anomali. Evaluasi menggunakan dataset transaksi e-commerce menunjukkan bahwa Hybrid AE-Transformer mencapai akurasi sebesar 95,2%, precision sebesar 89,0%, recall sebesar 74,0%, F1 score sebesar 80,0%, dan AUC sebesar 82,0%. Model ini menunjukkan peningkatan precision sebesar 12,0%, recall sebesar 7,0%, F1 score sebesar 8,0%, dan AUC sebesar 1,0% dibandingkan model terbaik lainnya seperti Ensemble. Validasi statistik melalui Uji Friedman dan Uji T-Test mengonfirmasi bahwa Hybrid AE-Transformer secara signifikan mengungguli model konvensional seperti DNN, LSTM, dan RNN dalam mendeteksi anomali pada transaksi e-commerce.References
M. Citation Gölyeri, S. Çelik, F. Bozyiğit, and D. Kılınç, “Fraud detection on e-commerce transactions using machine learning techniques,†Artif. Intell. Theory Appl., vol. 3, no. 1, pp. 45–50, 2023, [Online]. Available: https://www.boyner.com.tr/.
M. J. Madhurya, H. L. Gururaj, B. C. Soundarya, K. P. Vidyashree, and A. B. Rajendra, “Exploratory analysis of credit card fraud detection using machine learning techniques,†vol. 3, no. April, pp. 31–37, 2022, doi: 10.1016/j.gltp.2022.04.006.
A. Adesh, G. Shobha, J. Shetty, and L. Xu, “Journal of Parallel and Distributed Computing Local outlier factor for anomaly detection in HPCC systems,†J. Parallel Distrib. Comput., vol. 192, no. April 2023, p. 104923, 2024, doi: 10.1016/j.jpdc.2024.104923.
A. Iqbal and R. Amin, “Time series forecasting and anomaly detection using deep learning,†Comput. Chem. Eng., vol. 182, no. December 2023, p. 108560, 2024, doi: 10.1016/j.compchemeng.2023.108560.
K. Nian, H. Zhang, A. Tayal, T. Coleman, and Y. Li, “ScienceDirect Auto insurance fraud detection using unsupervised spectral ranking for anomaly,†J. Financ. Data Sci., vol. 2, no. 1, pp. 58–75, 2016, doi: 10.1016/j.jfds.2016.03.001.
T. Lin and J. Jiang, “Anomaly Detection with Autoencoder and Random Forest,†2020 Int. Comput. Symp., pp. 96–99, 2020, doi: 10.1109/ICS51289.2020.00028.
A. Wahid, M. Msahli, A. Bifet, and G. Memmi, “NFA : A neural factorization autoencoder based online telephony fraud detection,†Digit. Commun. Networks, vol. 10, no. 1, pp. 158–167, 2024, doi: 10.1016/j.dcan.2023.03.002.
I. Bhattacharya and A. Mickovic, “Accounting fraud detection using contextual language learning,†Int. J. Account. Inf. Syst., vol. 53, no. July 2022, p. 100682, 2024, doi: 10.1016/j.accinf.2024.100682.
M. Pota, G. De Pietro, and M. Esposito, “Engineering Applications of Artificial Intelligence Real-time anomaly detection on time series of industrial furnaces : A comparison of autoencoder architectures,†Eng. Appl. Artif. Intell., vol. 124, no. May, p. 106597, 2023, doi: 10.1016/j.engappai.2023.106597.
S. Misra, S. Thakur, M. Ghosh, and S. K. Saha, “An Autoencoder Based Based Model Model for for Detecting Detecting Fraudulent Fraudulent Credit Credit Card Card Transaction Transaction,†Procedia Comput. Sci., vol. 167, no. 2019, pp. 254–262, 2020, doi: 10.1016/j.procs.2020.03.219.
A. Sakhnenko, C. O. Meara, K. J. B. Ghosh, C. B. Mendl, G. Cortiana, and J. Bernab, “Hybrid Classical-Quantum Autoencoder for Anomaly Detection,†arXiv.org, pp. 1–17, 2021.
V. L. Cao, M. Nicolau, and J. McDermott, “A hybrid autoencoder and density estimation model for anomaly detection,†Lect. Notes Comput. Sci. (including Subser. Lect. Notes Artif. Intell. Lect. Notes Bioinformatics), vol. 9921 LNCS, pp. 717–726, 2016, doi: 10.1007/978-3-319-45823-6_67.
G. Li, P. Bai, J. Chen, and C. Liang, “Identifying virulence factors using graph transformer autoencoder with ESMFold-predicted structures,†Comput. Biol. Med., vol. 170, no. December 2023, p. 108062, 2024, doi: 10.1016/j.compbiomed.2024.108062.
S. Panigrahy and S. Karmakar, “Hydrophobicity classification of polymeric insulators using a masked autoencoder model in vision transformer,†Comput. Electr. Eng., vol. 116, no. February, p. 109165, 2024, doi: 10.1016/j.compeleceng.2024.109165.
W. Priatna, “Integrating Class Imbalance Solutions into Fraud Detection Systems : A Systematic Literature Review,†2024 2nd Int. Conf. Technol. Innov. Its Appl., pp. 1–6, 2024, doi: 10.1109/ICTIIA61827.2024.10761334.
A. Fitriyani, W. Priatna, T. S. Lestari, D. Handayani, T. B. A. Munandar, and Amri, “Data Balance Optimization of Fraud Classification for E-Commerce Transaction,†2022 7th Int. Conf. Informatics Comput. ICIC 2022, pp. 1–4, 2022, doi: 10.1109/ICIC56845.2022.10007028.
H. Fanai and H. Abbasimehr, “A novel combined approach based on deep Autoencoder and deep classifiers for credit card fraud detection,†Expert Syst. Appl., vol. 217, no. September 2022, p. 119562, 2023, doi: 10.1016/j.eswa.2023.119562.
H. Du, L. Lv, A. Guo, and H. Wang, “AutoEncoder and LightGBM for Credit Card Fraud Detection Problems,†Symmetry (Basel)., vol. 15, no. 4, 2023, doi: 10.3390/sym15040870.
D. Al-Safaar and W. L. Al-Yaseen, “Hybrid AE-MLP: Hybrid Deep Learning Model Based on Autoencoder and Multilayer Perceptron Model for Intrusion Detection System,†Int. J. Intell. Eng. Syst., vol. 16, no. 2, pp. 35–49, 2023, doi: 10.22266/ijies2023.0430.04.
S. Chen and W. Guo, “Auto-Encoders in Deep Learning—A Review with New Perspectives,†Mathematics, vol. 11, no. 8, pp. 1–54, 2023, doi: 10.3390/math11081777.
Z. Long, H. Yan, G. Shen, X. Zhang, H. He, and L. Cheng, “A Transformer-based network intrusion detection approach for cloud security,†J. Cloud Comput., vol. 13, no. 1, 2024, doi: 10.1186/s13677-023-00574-9.
T. Lin, Y. Wang, X. Liu, and X. Qiu, “A survey of transformers,†AI Open, vol. 3, no. October, pp. 111–132, 2022, doi: 10.1016/j.aiopen.2022.10.001.
R. Cao, J. Wang, M. Mao, G. Liu, and C. Jiang, “Feature-wise attention based boosting ensemble method for fraud detection,†Eng. Appl. Artif. Intell., vol. 126, no. PC, p. 106975, 2023, doi: 10.1016/j.engappai.2023.106975.
Z. Salekshahrezaee, J. L. Leevy, and T. M. Khoshgoftaar, “The effect of feature extraction and data sampling on credit card fraud detection,†J. Big Data, vol. 10, no. 1, 2023, doi: 10.1186/s40537-023-00684-w.
Y. Liu and L. Wu, “Intrusion Detection Model Based on Improved Transformer,†Appl. Sci., vol. 13, no. 10, 2023, doi: 10.3390/app13106251.
J. Liu and Y. Xu, “T-Friedman Test: A New Statistical Test for Multiple Comparison with an Adjustable Conservativeness Measure,†Int. J. Comput. Intell. Syst., vol. 15, no. 1, pp. 1–19, 2022, doi: 10.1007/s44196-022-00083-8.
