Home // DATA ANALYTICS 2013, The Second International Conference on Data Analytics // View article

DNA: An Online Algorithm for Credit Card Fraud Detection for Game Merchants

Authors:
Michael Schaidnagel
Ilia Petrov
Fritz Laux

Keywords: binary classification, credit card fraud, online environment

Abstract:
Online credit card fraud represents a significant challenge to online merchants. In 2011 alone, the total loss due to credit card fraud amounted to $ 7.60 billion with a clear upward trend. Especially online games merchants have difficulties applying standard fraud detection algorithms to achieve timely and accurate detection. The present paper introduces a novel approach for online fraud detection, called DNA. It is based on a formula which uses attributes that are derived from a sequence of transactions. The influence of these attributes on the result of the formula reveals additional information about this sequence. The result represents a fraud level indicator, serving as a classification threshold. A systematic approach for finding these attributes and the mode of operation of the algorithm is given in detail. The experimental evaluation against several standard algorithms on a real life data set demonstrates the superior fraud detection performance of the DNA approach (16.25 % better fraud detection accuracy, 99.59 % precision and low response time). In addition to that, several experiments were conducted in order to show the good scalability of the suggested algorithm.

Pages: 1 to 6

Copyright: Copyright (c) IARIA, 2013

Publication date: September 29, 2013

Published in: conference

ISSN: 2308-4464

ISBN: 978-1-61208-295-0

Location: Porto, Portugal

Dates: from September 29, 2013 to October 3, 2013