Ensemble Intelligent Agent Model for Detection of ATM Card Frauds in Nigeria

Abstract

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  hinder economic growth, creates distrust to the users. Several attempts have been made to investigate the issues and solutions proffered  using different approaches such as conventional measures, machine learning, and 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: (i) there is a shortage of knowledge concerning the access point where ATM fraud is committed and (ii) given its  infrequency and parallel nature most conventional investigators lack the experience to detect it. The aim of this thesis is to develop a high  performance intelligent agent-based model for detection of ATM card frauds in Nigeria, using SVM, KNN and logistic Regression    which will help immensely in providing a way forward in curbing the high rate of ATM fraud in Nigeria.