Detection and Control of Credit Card Fraud Attacks in Sliding Window with Exponential Forgetting
Artikel i vetenskaplig tidskrift, 2025
Confidence interval method in the moving window with exponential forgetting is proposed in this paper which allows to capture recent changes in the shopping behaviour of the cardholder, detect fraudulent amounts and mitigate the attack. Fraud risk scoring method is used for estimation of the intensity of the fraudulent activity via monitoring of the transaction rates, merchant category codes, times and some other factors for detection of the start of the attack.
The development and verification are based on detailed analysis of the transaction patterns from the dataset, which represents an extensive collection of around 24.4 million credit card transactions from IBM financial database. Recommendations for further development of the detection techniques are also presented.
fraud risk scoring
detection & control in moving window with exponential forgetting
monitoring of intensity of fraudulent activity
time series analysis
credit card fraud attacks
mitigation of fraud attack
Författare
Alexander Stotsky
Chalmers, Data- och informationsteknik, Interaktionsdesign och Software Engineering
International Journal of Computers and Applications
1206-212X (ISSN)
Vol. 186 74 0795-8887Styrkeområden
Informations- och kommunikationsteknik
Ämneskategorier (SSIF 2025)
Systemvetenskap, informationssystem och informatik
Artificiell intelligens
DOI
10.5120/ijca2025924619