Work

Data Mining for Fraud Detection: Toward an Improvement on Internal Control Systems?

Year: 2007
Type: conference-paper
Abstract: Fraud is a million dollar business and it's increasing every year. The numbers \nare shocking, all the more because over one third of all frauds are detected by \n'chance' means. The second best detection method is internal control. As \na result, it would be advisable to search for improvement of internal control \nsystems. Taking into consideration the promising success stories of companies \nselling data mining software, along with the positive results of research in this \narea, we evaluate the use of data mining techniques for the purpose of fraud \ndetection. Are we talking about real success stories, or salesmanship? For \nanswering this, first a theoretical background is given about fraud, internal \ncontrol, data mining and supervised versus unsupervised learning. Starting from \nthis background, it is interesting to investigate the use of data mining techniques \nfor detection of asset misappropriation, starting from unsupervised data. In this \nstudy, procurement fraud stands as an example of asset misappropriation. Data \nare provided by an international service-sector company. After mapping out the \npurchasing process, 'hot spots' are identified, resulting in some selected frauds \nas object of the study. As a first step towards fraud detection, outlier detection \nby means of clustering is practiced. The results show that this first analysis \nresults in a good division of the sample into regular cases and cases interesting \nto investigate further.
Language: English
Open Access status: green
OpenAlex ID: W2591317003
FWCI: 1.414
Cites: 34
Cited by: 23
Related to: 10