2

I want to write my thesis about Fraud Detection in ERP Databases. I'm looking for a Industry Standard Processs such as CRISP-DM for Data Mining Projects, in order to justify my approach in solving the issue of finding outliers/anomalies in the data set. Is there any established Standard Process which would be more suitable for such an project?

Thanks.

Nex
  • 285
  • 2
  • 6
  • 1
    what industry are you in? I imagine if standards exist, then they likely differ by subdomain, e.g., credit card fraud vs. insurance fraud – Brandon Loudermilk May 21 '16 at 14:21

2 Answers2

3

You should refer this survey paper on Anomaly Detection (from University of Minnesota).

Please let me know if this helps you.

Shagun Sodhani
  • 722
  • 4
  • 26
  • The paper appears to be very encouraging. I'll get in touch later on as the paper is very comprehensive. – Nex May 23 '16 at 07:07
1

Here's a great book on Fraud Analytics. It's quite comprehensive and has a detailed list of original research references and other textbooks at the end of each chapter.

Fraud Analytics Using Descriptive, Predictive, and Social Network Techniques: A Guide to Data Science for Fraud Detection Bart Baesens, Veronique Van Vlasselaer, Wouter Verbeke ISBN: 978-1-119-13312-4 Aug 2015

Bobby
  • 114
  • 6