Intelligent Authentication Agent Model for Detection of ATM Card Fraud in Nigeria

ATM card fraud is on the increase with the recent cashless policy and change of naira notes in Nigeria. Transactions are mostly done through cards, making it vulnerable to fraud hence; it is a major issue of concern to the banking sectors as well as to the users, which hinders economic growth, and creates distrust to in the users. Several attempts have been made to investigate the issues and solutions proffered using different approaches such as conventional measures, machine learning, improved firewall security, probability, etc. However, detecting and preventing ATM card frauds has proven to be difficult in both data collection and fraud investigation for the following reasons: there is a shortage of knowledge concerning the access point where ATM fraud is committed and given its infrequency and parallel nature most conventional investigators lack the experience to detect it. The aim of this research work is to develop a high performance intelligent agent-based model for detection of ATM card frauds. Basically, the model involves 3-factor authentication process to determine if a user should be granted access or otherwise, deny access to a bank ATM, these includes; Password module, AIAgent spending patter detection and lastly Biometric modules authentication. Logistic regression, SVM and KNN machine learning methodology were applied to historical log files of the ATM cards usage patterns to devise an intelligent data mining classification model. This model was evaluated using confusion matrix with the dataset from the bank. Its effectiveness was ascertained as the accuracy of K Nearness Neighbor (KNN), Support Vector Machine (SVM) and Logistic regression are 93%, 89% and 96% and precision 73%, 98% and 80% respectively. This will help immensely in providing a way forward in curbing the high rate of ATM card fraud in banking sector