论文信息 - Using Bayesian Belief Networks for credit card fraud detection

Using Bayesian Belief Networks for credit card fraud detection

The number of credit card fraud cases is permanently increasing. Therefore, at this moment the problem of fraud prevention system implementation with automatic decision maker functions is really actual. In this paper the disadvantage of Bayesian Belief Networks for the fraud detection and the developed input data representation method are considered. At the end of this paper the results of the evaluative testing and corresponding conclusions are described.

L. E. Mukhanov

[1] Wai Lam,et al. LEARNING BAYESIAN BELIEF NETWORKS: AN APPROACH BASED ON THE MDL PRINCIPLE , 1994, Comput. Intell..

[2] Joe Suzuki,et al. Learning Bayesian Belief Networks Based on the MDL Principle : An Efficient Algorithm Using the Branch and Bound Technique , 1999 .

[3] Pat Langley,et al. Estimating Continuous Distributions in Bayesian Classifiers , 1995, UAI.

[4] Salvatore J. Stolfo,et al. Toward Scalable Learning with Non-Uniform Class and Cost Distributions: A Case Study in Credit Card Fraud Detection , 1998, KDD.

[5] Rüdiger W. Brause,et al. Neural data mining for credit card fraud detection , 1999, Proceedings 11th International Conference on Tools with Artificial Intelligence.