Human behavior scoring in credit card fraud detection

<span lang="EN-US">Now days, the analysis of behavior cardholders is one important fields in electronic payment. This kind helps to extract behavioral and transaction profile patterns that can help financial systems better protect their customers. In this paper, we propose an intelligent machine learning (ML) system for rules generation. It based on a hybrid approach using rough set theory feature selection, fuzzy logic association A score function defined computed each number rules, make suspicious. risk factor used measure level awareness improve card fraud detection general. The part whole where it combined classification detection. work, also implementation integrating layer. results obtained are very convincing consumed time by our system, per was 6 ms, which prove able handle real process.</span>