A Classification System for Credit Card Transactions

This paper describes a system that responds to a significant problem involving credit card theft. After a card has been stolen, some of the transactions processed subsequently have to be granted if it seems that they were carried out by the card owner himself (e.g. by a standing order) while other transactions should be denied authorization if they were carried out by the misuser of the card. The system developed makes use of a neural network integrated with a Case-Based Reasoning (CBR) component. While the CBR system can use specific cases to determine when a transaction should be granted or denied authorization, the neural network can recognise general patterns of behaviour for the use and the misuse of credit cards and can use this knowledge in the classification task. This paper presents the architecture of the classification system proposed, highlighting the main aspects of each of its components. The system's performance is evaluated and conclusions are drawn.

[1]  H. Tirri,et al.  Massively Parallel Case-Based Reasoning with Probabilistic Similarity Metrics , 1993, EWCBR.

[2]  Beatriz de Faria Leão,et al.  Calculating the Mean Knowledge Representation from Multiple Experts , 1990 .

[3]  Janet L. Kolodner,et al.  Case-Based Reasoning , 1989, IJCAI 1989.

[4]  Abraham Kandel,et al.  Hybrid Architectures for Intelligent Systems , 1992 .

[5]  J. Kacprzyk,et al.  Multiperson decision making models using fuzzy sets and possibility theory , 1990 .

[6]  B. Leao,et al.  A hybrid connectionist expert system to solve classification problems , 1993, Proceedings of Computers in Cardiology Conference.

[7]  Geoffrey E. Hinton,et al.  Learning internal representations by error propagation , 1986 .

[8]  Mario Lenz.  Cabata | a Hybrid Cbr System , 1995 .

[9]  R. J. Machado.  Handling knowledge in high order neural networks: the combinatorial neural model , 1989, International 1989 Joint Conference on Neural Networks.

[10]  Armando Freitas da Rocha,et al.  A Hybrid Architecture for Fuzzy Connectionist Expert System , 1992 .

[11]  G. A. Miller.  THE PSYCHOLOGICAL REVIEW THE MAGICAL NUMBER SEVEN, PLUS OR MINUS TWO: SOME LIMITS ON OUR CAPACITY FOR PROCESSING INFORMATION 1 , 1956 .

[12]  James L. McClelland,et al.  Parallel distributed processing: explorations in the microstructure of cognition, vol. 1: foundations , 1986 .

[13]  Roger King,et al.  Semantic database modeling: survey, applications, and research issues , 1987, CSUR.