The paper presents multi-agent techniques for fraud analysis. We present a mathematical model for credit card detection and compare different intelligent agents such as monitoring agents, collating agent, diagnosing agent and reporting agent. We tested agents as against cases of credit card fraud over time at different rates with which customer received fraud alerts, we discovered improvement in detecting a credit card fraud cases using multi-agents system. The credit card authentication techniques is weak and give room to unauthorised users to gain access to customers account and steal their money through online transactions. No single platform for credit card fraud detection + Intelligent Agents +Data Mining. The objective of this paper is to model a security system that will promote trust in communication channels by implementing hybrid technology that will combine both adaptive data mining and intelligent agents to authenticate the credit card transaction. The model was therefore recommended for implementation in use by Banks, financial agencies and government agencies for the security and diagnosis of credit card fraud. This shows that the performance of credit card fraud (CCF) detection using multi-agents is in agreement with other detection software, but performs 94% better.

Multi-agents, credit card fraud, fraudulent transactions, data mining, confusion matrix & ROC curve

[1] Lee, W., Stolfo, S., & Mok, K. (2011). Adaptive Intrusion Detection: a Data mining Approach, Kulwer Academic Publishers.
[2] Singh Mandeep, Perminderpal Singh & Rajan Kumar (2014). Fraud detection by monitoring user behavior and activities. International Conference on Computer and Intelligent Systems, 6-14.
[3] Farvaresh, H., & Sepehri, M.M (2010). A Data Mining Framework for deleting Subscription Fraud in Telecommunication. Science Direct, Engineering Applications of Artificial intelligence. (24), 182-194.
[4] Quah, J.T.S., & Sriganesh, M. (2008). Real Time Credit Card Fraud detection using Computational Intelligence. Expert Systems with applications, 35(4), 112-118.
[5] Srivastava, J., & Raghubir, P. (2008). Monopoly Money, the Effect of Payment Coupling and form on spending behavior. Journal of Experimental Psycology, 27(4), 460-474
[6] Nabha, K., Neha, P., Shraddha, K., Suja, S., & Amol, P. (2015). Credit card fraud detection system using Hidden Markov Model and Adaptive Communal Detection. International Journal of Computer Science and Information Technologies, 6 (2), 1795-1797.
[7] Singh, H., & Rajan. (2014). Impact of information technology on Indian banking services. Proceedings of the 1st International Conference on Recent Advances in Information Technology, IEEE Xlore Press, Dhanbad, 662-665.
[8] Sahil Hak, Suraj Singh, & Varun Purohit. (2015). Credit card fraud detection using Advanced Combination Heuristic and Bayes’ Theorem. International Journal of Innovative Research in Computer and Communication Engineering. 3(4), 2756-2763
[9] Ekrem, D., & Mehmet Hamdi Ozcelik (2011). Detecting Credit Card fraud by genetic algorithms and scatter search. Expert Systems with applications: An International Journal, 38(10), 13057-13063.