Year: 2025
Type: article
Abstract: The financial fraud prediction is important research is needy one for current research.Because every minute's lakhs of fraud activities are happening in the worldwide.The different approaches are used to predict and analysis the credit card fraud activities.In credit card fraud prediction behaviour analysis is an important one.In this work, presented new prediction model based on the real time behaviour analysis and with the help of history transaction dataset.The behaviour analysis is performed based on the proactive data such as user typing speed of username and password, normal, abnormal activities and other properties.The proposed model prediction is performed based on the fuzzy logic and deep neural network system.The fuzzy logic used to check the behaviour of human and find the member activities.The deep neural network is used to identifying anomalous behaviour of credit card activities.For implementation, a real-time dataset from a commercial bank used static and dynamic features are used.The accuracy, sensitivity, and specificity metrics are used to measure the performance of proposed work.
Authors: N. Prabha, S. Manimekalai
Institution: Thiruvalluvar University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: diamond
OpenAlex ID: W4407142974