Credit Card Fraud Detection Based on MiniKM-SVMSMOTE-XGBoost Model
Yanzhao Gu, Junhao Wei, Ngai Cheong · 2024
In recent years, the problem of credit card fraud has become more acute with the digitisation of credit cards. For the high data volume, high dimensionality and extreme imbalance of credit card transaction data. This paper explores the application in the field of credit card fraud detection based on MiniBatchKMeans-SVMSMOTE-XGBoost model. Through combining clustering, oversampling and classification algorithms, an improved fraud detection method is proposed. The experimental results show that the model performs well in handling unbalanced data with high accuracy and generalisation ability.