Fraud Detection for MCC Manipulation

Abstract

MCC manipulation arising in recent years is a new kind of fraud happened in financial system. Aiming at this issue, this study proposes a computational framework to detect such fraud behavior. The framework utilizes hierarchical clustering to discover the inherent transaction behavior pattern existed in various businesses and predicts the fraud merchant by applying logistic regression model. The experimental results indicate that the model overall outperforms other classifiers in detecting merchant's MCC manipulation.