A Game-Theoretic Approach to Credit Card Fraud Detection

Intrusion prevention mechanisms are largely insufficient for protection of databases against Information Warfare attacks by authorized users and has drawn interest towards intrusion detection. We visualize the conflicting motives between an attacker and a detection system as a multi-stage game between two players, each trying to maximize his payoff. We consider the specific application of credit card fraud detection and propose a fraud detection system based on a game-theoretic approach. Not only is this approach novel in the domain of Information Warfare, but also it improvises over existing rule-based systems by predicting the next move of the fraudster and learning at each step.