An Intelligent System for Detecting Irregularities in Electronic Banking Transactions

Abstract

Frauds have historically been the major cause of bank losses. It has led to failures of some banks in the pasts, contributing toshareholders losing their investments in the banks. Information technology is a critical component in creating value in thebanking sectors, it provides decision makers with an efficient means to store, calculate, report and predict bank frauds andsecurity failures. Information system security views this challenge as a prediction problem that attempts to detect irregulartransactions in the banking sector operations scenario. This study applies neural network techniques to the bank fraudprediction problem. Using Nigerian banks as a point of reference, we design a Neural Network-Based Model that employsmultilayered Feed Forward Artificial Neural Network on database system for collecting training data for the Artificial NeuralNetwork. The Intelligence of the system is being tested on data extracted from statements of accounts from three differentbanks in Nigeria and the results were discussed.Keywords: Artificial neural network, transactions, bank fraud, financial institutions & cyber security