
Ketidakseimbangan data menjadi tantangan utama dalam deteksi transaksi penipuan karena jumlah transaksi legal jauh lebih dominan. Penelitian ini membandingkan efektivitas metode ADASYN dan CTGAN dalam menyeimbangkan data dan meningkatkan performa model klasifikasi. Dataset berisi 6,3 juta transaksi dianalisis melalui preprocessing, seleksi fitur XGBoost, stratified sampling, balancing, dan modeling menggunakan Decision Tree, Random Forest, serta MLP Classifier. Hasil menunjukkan bahwa meskipun kedua metode meningkatkan distribusi kelas, performa metrik Precision dan F1 Score masih belum optimal. Diperlukan penerapan hyperparameter tuning serta eksplorasi metode balancing lain untuk hasil yang lebih baik.
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
