X-SHAoLIM: Novel Feature Selection Framework for Credit Card Fraud Detection
Publish Year: 1403
نوع سند: مقاله ژورنالی
زبان: English
View: 40
This Paper With 11 Page And PDF Format Ready To Download
- Certificate
- من نویسنده این مقاله هستم
استخراج به نرم افزارهای پژوهشی:
شناسه ملی سند علمی:
JR_JADM-12-1_005
تاریخ نمایه سازی: 10 خرداد 1403
Abstract:
Fraud in financial data is a significant concern for both businesses and individuals. Credit card transactions involve numerous features, some of which may lack relevance for classifiers and could lead to overfitting. A pivotal step in the fraud detection process is feature selection, which profoundly impacts model accuracy and execution time. In this paper, we introduce an ensemble-based, explainable feature selection framework founded on SHAP and LIME algorithms, called "X-SHAoLIM". We applied our framework to diverse combinations of the best models from previous studies, conducting both quantitative and qualitative comparisons with other feature selection methods. The quantitative evaluation of the "X-SHAoLIM" framework across various model combinations revealed consistent accuracy improvements on average, including increases in Precision (+۵.۶), Recall (+۱.۵), F۱-Score (+۳.۵), and AUC-PR (+۶.۷۵). Beyond enhanced accuracy, our proposed framework, leveraging explainable algorithms like SHAP and LIME, provides a deeper understanding of features' importance in model predictions, delivering effective explanations to system users.
Keywords:
Authors
Sajjad Alizadeh Fard
School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran.
Hossein Rahmani
School of Computer Engineering, Iran University of Science and Technology, Tehran, Iran.
مراجع و منابع این Paper:
لیست زیر مراجع و منابع استفاده شده در این Paper را نمایش می دهد. این مراجع به صورت کاملا ماشینی و بر اساس هوش مصنوعی استخراج شده اند و لذا ممکن است دارای اشکالاتی باشند که به مرور زمان دقت استخراج این محتوا افزایش می یابد. مراجعی که مقالات مربوط به آنها در سیویلیکا نمایه شده و پیدا شده اند، به خود Paper لینک شده اند :