Some Experimental Issues in Financial Fraud Detection: An Investigation

TL;DR

This paper critically examines key performance metrics and computational techniques for credit card fraud detection, highlighting their effectiveness and offering insights for improving detection systems.

Contribution

It revisits and critiques existing performance metrics and evaluates various computational intelligence and classification methods for financial fraud detection.

Findings

Analysis of popular performance metrics for fraud detection

Comparison of computational intelligence techniques effectiveness

Evaluation of binary classification methods in credit card fraud detection

Abstract

Financial fraud detection is an important problem with a number of design aspects to consider. Issues such as algorithm selection and performance analysis will affect the perceived ability of proposed solutions, so for auditors and re-searchers to be able to sufficiently detect financial fraud it is necessary that these issues be thoroughly explored. In this paper we will revisit the key performance metrics used for financial fraud detection with a focus on credit card fraud, critiquing the prevailing ideas and offering our own understandings. There are many different performance metrics that have been employed in prior financial fraud detection research. We will analyse several of the popular metrics and compare their effectiveness at measuring the ability of detection mechanisms. We further investigated the performance of a range of computational intelligence techniques when applied to this problem domain, and explored the efficacy of several binary classification methods.