Analisis Komparatif Metode Deep Learning dan Machine Learning dalam Deteksi Pencucian Uang dengan Teknik Rekayasa Fitur

• FATIMAH ASMITA RANI
• 14230012

---

ABSTRAK

ABSTRAK

• Nama             : Fatimah Asmita Rani
• NIM                 : 14230012
• Program Studi : Ilmu Komputer
• Fakultas           : Teknologi Informasi
• Jenjang            : Strata Dua (S2)

Peminatan : Artificial Intelligence dan Blockchain Judul : Analisis Komparatif Metode Deep Learning dan Machine Learning dalam Deteksi Pencucian Uang dengan Teknik Rekayasa Fitur

Pencucian uang dikenal sebagai kegiatan untuk mendapatkan uang secara ilegal yang masuk ke dalam sistem keuangan dan kemudian dipalsukan melalui berbagai transaksi yang tampak sah, sehingga sumber uang tersebut menjadi sulit dilacak. Penelitian ini menggunakan dua teknik Machine Learning (ML) dan Deep Learning (DL) pada dataset Elliptic untuk mendeteksi transaksi ilegal dan non-ilegal dalam mata uang kripto. Tujuan dari penelitian ini adalah untuk mengevaluasi seberapa efektif model dalam mengidentifikasi aktivitas yang mencurigakan dan untuk mengatasi masalah data yang memiliki dimensi tinggi dan data yang tidak seimbang. Jumlah total dataset Elliptic adalah 203.769 record dan 166 atribut. Dari data tersebut terdapat dua kelas, yaitu legal, ilegal dan tidak dikenal. Kemudian, dilakukan preprocessing data dengan menghilangkan 157.205 label yang tidak dikenal sehingga data yang digunakan pada label transaksi legal dan ilegal adalah 42.019 data. Tahapan preprocessing meliputi standarisasi fitur, pengkodean label, reduksi dimensionalitas menggunakan PCA, dan menggunakan SMOTE untuk penyeimbangan data. Tahap selanjutnya adalah tahap pemodelan menggunakan algoritma pembelajaran mesin Random Forest (RF), Support Vector Machine (SVM), k-Nearest Neighbors (KNN), Naive Bayes (NB), Decision Tree serta algoritma pembelajaran mendalam Long Short-Term Memory (LSTM) dan Deep Neural Network (DNN). Tahap terakhir adalah validasi silang untuk menguji kinerja model dan menggunakan penyetelan hiperparameter untuk mendapatkan model terbaik. Berdasarkan hasil penelitian, model terbaik adalah algoritma LSTM dengan akurasi tertinggi sebesar 99%

KATA KUNCI

METODE DEEP LEARNING

---

DAFTAR PUSTAKA

DAFTAR PUSTAKA

[1] B. Dumitrescu, A. Baltoiu, and S. Budulan, “Anomaly Detection in Graphs of Bank Transactions for Anti Money Laundering Applications,” IEEE Access, vol. 10, pp. 47699–47714, 2022, doi: 10.1109/ACCESS.2022.3170467.

[2] J. de J. Rocha-Salazar, M. J. Segovia-Vargas, and M. del M. Camacho-Miñano, “Money laundering and terrorism financing detection using neural networks and an abnormality indicator,” Expert Syst. Appl., vol. 169, 2021, doi: 10.1016/j.eswa.2020.114470.

[3] W. Firmansyah and H. T. Atmadja, “Juridical Analysis Awareness of Profession Advocacy to Financial Transaction Reports and Analysis Centre (PPATK) During Prevent and Eradicate Money …,” J. Multidiscip. …, pp. 308–314, 2021, doi: 10.51971/joma.v5n3.24092021.

[4] A. Alabdulwahab, M. A. Haq, and M. Alshehri, “Cyberbullying Detection using Machine Learning and Deep Learning,” Int. J. Adv. Comput. Sci. Appl., vol. 14, no. 10, pp. 424–432, 2023, doi: 10.14569/IJACSA.2023.0141045.

[5] R. I. T. Jensen and A. Iosifidis, “Fighting Money Laundering With Statistics and Machine Learning,” IEEE Access, vol. 11, no. January, pp. 8889–8903, 2023, doi: 10.1109/ACCESS.2023.3239549.

[6] M. Alkhalili, M. H. Qutqut, and F. Almasalha, “Investigation of Applying Machine Learning for Watch-List Filtering in Anti-Money Laundering,” IEEE Access, vol. 9, pp. 18481–18496, 2021, doi: 10.1109/ACCESS.2021.3052313.

[7] J. Lorenz, M. I. Silva, D. Aparício, J. T. Ascensão, and P. Bizarro, “Machine learning methods to detect money laundering in the bitcoin blockchain in the presence of label scarcity,” ICAIF 2020 - 1st ACM Int. Conf. AI Financ., 2020, doi: 10.1145/3383455.3422549.

[8] D. V. Kute, B. Pradhan, N. Shukla, and A. Alamri, “Deep Learning and Explainable Artificial Intelligence Techniques Applied for Detecting Money Laundering-A Critical Review,” IEEE Access, vol. 9, pp. 82300–82317, 2021, doi: 10.1109/ACCESS.2021.3086230.

[9] J. Domashova and N. Mikhailina, “Usage of machine learning methods for early detection of money laundering schemes,” Procedia Comput. Sci., vol. 190, no. 2020, pp. 184–192, 2021, doi: 10.1016/j.procs.2021.06.033.

[10] M. Weber et al., “Anti-Money Laundering in Bitcoin: Experimenting with Graph Convolutional Networks for Financial Forensics,” no. July, 2019, doi: 65 10.48550/arXiv.1908.02591.

[11] S. Wang, Y. Dai, J. Shen, and J. Xuan, “Research on expansion and classification of imbalanced data based on SMOTE algorithm,” Sci. Rep., vol. 11, no. 1, pp. 1–11, 2021, doi: 10.1038/s41598-021-03430-5.

[12] K. Younes et al., “Application of Unsupervised Learning for the Evaluation of Aerogels’ Efficiency towards Dye Removal—A Principal Component Analysis (PCA) Approach,” Gels, vol. 9, no. 4, 2023, doi: 10.3390/gels9040327.

[13] F. Aldi, F. Hadi, N. A. Rahmi, and S. Defit, “Standardscaler’S Potential in Enhancing Breast Cancer Accuracy Using Machine Learning,” J. Appl. Eng. Technol. Sci., vol. 5, no. 1, pp. 401–413, 2023, doi: 10.37385/jaets.v5i1.3080.

[14] B. M. S. Hasan and A. M. Abdulazeez, “A Review of Principal Component Analysis Algorithm for Dimensionality Reduction,” J. Soft Comput. Data Min., vol. 2, no. 1, pp. 20–30, 2021, doi: 10.30880/jscdm.2021.02.01.003.

[15] H. Santoso, I. Hanif, H. Magdalena, and Afiyati, “A Hybrid Model for Dry Waste Classification using Transfer Learning and Dimensionality Reduction,” Int. J. Informatics Vis., vol. 8, no. 2, pp. 623–634, 2024, doi: 10.62527/joiv.8.2.1943.

[16] V. Jackins, S. Vimal, M. Kaliappan, and M. Y. Lee, “AI-based smart prediction of clinical disease using random forest classifier and Naive Bayes,” J. Supercomput., vol. 77, no. 5, pp. 5198–5219, 2021, doi: 10.1007/s11227-020-03481-x.

[17] E. Y. Boateng, J. Otoo, and D. A. Abaye, “Basic Tenets of Classification Algorithms KNearest-Neighbor, Support Vector Machine, Random Forest and Neural Network: A Review,” J. Data Anal. Inf. Process., vol. 08, no. 04, pp. 341–357, 2020, doi: 10.4236/jdaip.2020.84020.

[18] S. Uddin, I. Haque, H. Lu, M. A. Moni, and E. Gide, “Comparative performance analysis of K-nearest neighbour (KNN) algorithm and its different variants for disease prediction,” Sci. Rep., vol. 12, no. 1, pp. 1–11, 2022, doi: 10.1038/s41598-022-10358-x.

[19] P. G. Schyns, L. Snoek, and C. Daube, “Degrees of algorithmic equivalence between the brain and its DNN models,” Trends Cogn. Sci., vol. 26, no. 12, pp. 1090–1102, 2022, doi: 10.1016/j.tics.2022.09.003.

[20] J. M. T. Wu, Z. Li, N. Herencsar, B. Vo, and J. C. W. Lin, “A graph-based CNN-LSTM stock price prediction algorithm with leading indicators,” Multimed. Syst., vol. 29, no. 3, pp. 1751–1770, 2023, doi: 10.1007/s00530-021-00758-w.

[21] I. Huda, A. A. Suhendra, and M. A. Bijaksana, “Design of Prediction Model using Data Mining for Segmentation and Classification Customer Churn in E-Commerce Mall in 66 Mall,” Int. J. Informatics Vis., vol. 7, no. 4, pp. 2280–2289, 2023, doi: 10.30630/joiv.7.4.2414.

[22] S. Elnaffar and M. Fawey, “Uncovering the Most Effective Pedagogical Techniques for Math Education Using Machine Learning,” Int. J. Informatics Vis., vol. 8, no. 3–2, pp. 1671–1677, 2024, doi: 10.62527/joiv.8.3-2.3123.

[23] T. R. Mahesh et al., “AdaBoost Ensemble Methods Using K-Fold Cross Validation for Survivability with the Early Detection of Heart Disease,” Comput. Intell. Neurosci., vol. 2022, 2022, doi: 10.1155/2022/9005278.

[24] I. K. Nti, O. Nyarko-Boateng, and J. Aning, “Performance of Machine Learning Algorithms with Different K Values in K-fold CrossValidation,” Int. J. Inf. Technol. Comput. Sci., vol. 13, no. 6, pp. 61–71, 2021, doi: 10.5815/ijitcs.2021.06.05.

[25] S. Saud, B. Jamil, Y. Upadhyay, and K. Irshad, “Performance improvement of empirical models for estimation of global solar radiation in India: A k-fold cross-validation approach,” Sustain. Energy Technol. Assessments, vol. 40, no. April, p. 100768, 2020, doi: 10.1016/j.seta.2020.100768.

[26] M. Jullum, A. Løland, R. B. Huseby, G. Ånonsen, and J. Lorentzen, “Detecting money laundering transactions with machine learning,” J. Money Laund. Control, vol. 23, no. 1, pp. 173–186, 2020, doi: 10.1108/JMLC-07-2019-0055.

[27] J. J. Soria, R. Loayza Abal, and L. Segura Peña, “Machine Learning Models for Money Laundering Detection in Financial Institutions. A Systematic Literature Review,” Proc. LACCEI Int. Multi-conference Eng. Educ. Technol., pp. 1–10, 2024, doi: 10.18687/LACCEI2024.1.1.1682.

[28] I. Alarab, S. Prakoonwit, and M. I. Nacer, “Comparative Analysis Using Supervised Learning Methods for Anti-Money Laundering in Bitcoin,” ACM Int. Conf. Proceeding Ser., pp. 11–17, 2020, doi: 10.1145/3409073.3409078.

[29] A. N. Bakry, A. S. Alsharkawy, M. S. Farag, and K. R. Raslan, “Automatic suppression of false positive alerts in anti-money laundering systems using machine learning,” J. Supercomput., vol. 80, no. 5, pp. 6264–6284, 2024, doi: 10.1007/s11227-023-05708-z.

[30] A. Kumar, S. Das, and V. Tyagi, “Anti money laundering detection using naïve bayes classifier,” 2020 IEEE Int. Conf. Comput. Power Commun. Technol. GUCON 2020, pp. 568–572, 2020, doi: 10.1109/GUCON48875.2020.9231226.

[31] A. Amato and V. Di Lecce, “Data preprocessing impact on machine learning algorithm performance,” Open Comput. Sci., vol. 13, no. 1, 2023, doi: 10.1515/comp-2022-0278.

[32] A. B. Wiratman and Wella, “Personalized Learning Models Using Decision Tree and 67 Random Forest Algorithms in Telecommunication Company,” Int. J. Informatics Vis., vol. 8, no. 1, pp. 318–325, 2024, doi: 10.62527/joiv.8.1.1905.

[33] A. S. Barkah, S. R. Selamat, Z. Z. Abidin, and R. Wahyudi, “Impact of Data Balancing and Feature Selection on Machine Learning-based Network Intrusion Detection,” Int. J. Informatics Vis., vol. 7, no. 1, pp. 241–248, 2023, doi: 10.30630/joiv.7.1.1041.

[34] E. Ileberi, Y. Sun, and Z. Wang, “Performance Evaluation of Machine Learning Methods for Credit Card Fraud Detection Using SMOTE and AdaBoost,” IEEE Access, vol. 9, pp. 165286–165294, 2021, doi: 10.1109/ACCESS.2021.3134330.

[35] D. A. Anggoro and S. S. Mukti, “Performance Comparison of Grid Search and Random Search Methods for Hyperparameter Tuning in Extreme Gradient Boosting Algorithm to Predict Chronic Kidney Failure,” Int. J. Intell. Eng. Syst., vol. 14, no. 6, pp. 198–207, 2021, doi: 10.22266/ijies2021.1231.19.

[36] D. Valero-Carreras, J. Alcaraz, and M. Landete, “Comparing two SVM models through different metrics based on the confusion matrix,” Comput. Oper. Res., vol. 152, no. December 2022, p. 106131, 2023, doi: 10.1016/j.cor.2022.106131.

[37] M. Hasnain, M. F. Pasha, I. Ghani, M. Imran, M. Y. Alzahrani, and R. Budiarto, “Evaluating Trust Prediction and Confusion Matrix Measures for Web Services Ranking,” IEEE Access, vol. 8, pp. 90847–90861, 2020, doi: 10.1109/ACCESS.2020.2994222.

[38] I. Priyadarshini and C. Cotton, “A novel LSTM–CNN–grid search-based deep neural network for sentiment analysis,” J. Supercomput., vol. 77, no. 12, pp. 13911–13932, 2021, doi: 10.1007/s11227-021-03838-w.

[39] S. Prabu, B. Thiyaneswaran, M. Sujatha, C. Nalini, and S. Rajkumar, “Grid Search for Predicting Coronary Heart Disease by Tuning Hyper-Parameters,” Comput. Syst. Sci. Eng., vol. 43, no. 2, pp. 737–749, 2022, doi: 10.32604/csse.2022.022739.

[40] I. Alarab, S. Prakoonwit, and M. I. Nacer, “Competence of graph convolutional networks for anti-money laundering in bitcoin blockchain,” ACM Int. Conf. Proceeding Ser., no. January 2021, pp. 23–27, 2020, doi: 10.1145/3409073.3409080.

[41] I. Alarab and S. Prakoonwit, “Effect of data resampling on feature importance in imbalanced blockchain data: Comparison studies of resampling techniques,” Data Sci. Manag., vol. 5, no. 2, pp. 66–76, 2022, doi: 10.1016/j.dsm.2022.04.003.