EPrints Universitas Amikom YogyakartaDETEKSI KECURANGAN KEUANGAN DENGAN MENGGUNAKAN METODE RANDOM FOREST DAN XGBOOST PADA DATA YANG TIDAKSEIMBANGMuhammad AlghifariAl AsqolaniauthorPenelitian ini bertujuan mendeteksi fraud dengan teknik ensemble machine learning, khususnya Random Forest (RF) dan Extreme Gradient Boosting (XGBoost), diterapkan pada dataset Credit Card Fraud Detection Kaggle (284.807 sampel, 0,17% fraud). Proses metodologi mencakup preprocessing melalui normalisasi dan Synthetic Minority Over-sampling Technique (SMOTE) untuk menangani ketidakseimbangan, diikuti pelatihan model menggunakan Scikit-learn serta XGBoost di Python. RF efektif mencegah overfitting lewat bagging, sementara XGBoost unggul dalam optimasi gradient untuk data skala besar. Evaluasi dilakukan dengan metrik Area Under the Curve (AUC-ROC), precision, recall, dan F1-score melalui cross-validation. Hasil menunjukkan XGBoost lebih superior (AUC-ROC 0,98; precision 0,95; recall 0,92; F1-score 0,93) dibanding RF (0,96; 0,92; 0,89; 0,90), berkat ketangguhannya terhadap noise. Penelitian menyimpulkan XGBoost sebagai metode optimal untuk data imbalanced, dengan saran integrasi SMOTE guna tingkatkan recall hingga 15%. Kontribusi teoritis memperkaya literatur machine learning di keamanan siber (Al-Hashedi & Magalingam, 2021), sementara manfaat praktisnya mengurangi kerugian bagi bank dan fintech, serta mendukung pengembangan model real-time.000 Ilmu komputer, informasi dan pekerjaan umum003 Sistem-sistem2025-12-16Universitas AMIKOM Yogyakarta;Fakultas Ilmu KomputerThesis

For work being deposited by its own author: In self-archiving this collection of files and associated bibliographic metadata, I grant EPrints Universitas Amikom Yogyakarta the right to store them and to make them permanently available publicly for free on-line. I declare that this material is my own intellectual property and I understand that EPrints Universitas Amikom Yogyakarta does not assume any responsibility if there is any breach of copyright in distributing these files or metadata. (All authors are urged to prominently assert their copyright on the title page of their work.)

For work being deposited by someone other than its author: I hereby declare that the collection of files and associated bibliographic metadata that I am archiving at EPrints Universitas Amikom Yogyakarta) is in the public domain. If this is not the case, I accept full responsibility for any breach of copyright that distributing these files or metadata may entail.

Clicking on the deposit button indicates your agreement to these terms.