A customized classification algorithm for credit card fraud detection. (June 2018)

• Record Type: Journal Article
• Authors: de Sá, Alex G.C.; Pereira, Adriano C.M.; Pappa, Gisele L.
• Is Part Of: Engineering applications of artificial intelligence. Volume 72(2018)
• Page Start: 21
• Page End: 29
• Publication Date: 2018-06
• Subjects: Credit card fraud -- Bayesian network classifiers -- Hyper-heuristic; Engineering -- Data processing -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Ingénierie -- Informatique -- Périodiques; Intelligence artificielle -- Périodiques; Systèmes experts (Informatique) -- Périodiques; Artificial intelligence; Engineering -- Data processing; Expert systems (Computer science); Periodicals; 620.00285
• DOI: 10.1016/j.engappai.2018.03.011
• Languages: English
• ISSNs: 0952-1976

Abstract

Abstract: This paper presents Fraud-BNC, a customized Bayesian Network Classifier (BNC) algorithm for a real credit card fraud detection problem. The task of creating Fraud-BNC was automatically performed by a Hyper-Heuristic Evolutionary Algorithm (HHEA), which organizes the knowledge about the BNC algorithms into a taxonomy and searches for the best combination of these components for a given dataset. Fraud-BNC was automatically generated using a dataset from PagSeguro, the most popular Brazilian online payment service, and tested together with two strategies for dealing with cost-sensitive classification. Results obtained were compared to seven other algorithms, and analyzed considering the data classification problem and the economic efficiency of the method. Fraud-BNC presented itself as the best algorithm to provide a good trade-off between both perspectives, improving the current company's economic efficiency in up to 72.64%. Graphical abstract: Highlights: We use a hyper-heuristic to create Fraud-BNC, a customized classification algorithm. Fraud-BNC is generated considering a real credit card fraud detection problem. Fraud-BNC's model has the main advantage of being interpretable by decision markers. Fraud-BNC is evaluated using both classification and economical measures. The algorithm improved the current company's economical efficiency in up to 72.64%.