Detection and Prevention WEB-Service for Fraudulent E-Transaction using APRIORI and SVM

Abstract

With the increased use of information technology, many financial services are available to users at their fingertips. However, this led to many fraud transactions. Automatic fraud identification and detection could improve the user experience and security of online transactions. Using machine learning algorithms, it is possible to detect fraud transactions. Machine learning algorithms have the ability to find the hidden implicit pattern and data relationships from a large dataset. Hence, using this algorithm is possible to detect the outlier from all transactions, which can help in determining the fraud transaction. In this paper, the APRIORI algorithm and Support Vector Machine are used to detect fraud transactions in credit cards via developing a secure web application service enforced the security by standard metrics. We compare the result with the other existing machine learning algorithms. We observed that the accuracy of fraud transaction detection is higher in the proposed algorithm more than 94.56, and the false fraud transaction detection is less than the fraud detection based on the Hidden Markov Model.