We discuss the use of predictive analytics (using a labeled data set), descriptive analytics (using an unlabeled data set) and social network analytics (using a networked data set). The techniques discussed can be applied across a wide variety of fraud applications, such as insurance fraud, credit card fraud, anti-money laundering, healthcare fraud, telecommunications fraud, click fraud, tax evasion, counterfeit,…
Fraud detection is more valuable the sooner it happens, because further losses are prevented, potential recoveries are higher, and security issues can be addressed more rapidly, as such avoiding cascading damage to an organization. Detecting fraud in an early stage however is harder than detecting it in an evolved stage, and requires specific techniques discussed in this book.
Furthermore, analytics are the most efficient way to detect fraud as soon as possible and as accurately as possible. And since data is becoming available to any organization abundantly and at a low cost, fraud analytics as well are within reach of any organization – at least with the right skills available. This book teaches exactly those skills.
As mentioned, we also provide a detailed overview of the different types of fraud detection techniques: predictive, descriptive and social network analytics, providing the reader a 360 degree view of the field. One of the most powerful information sources for detecting fraud concerns social network analysis. How to use such information by leveraging state-of-the-art social network analysis techniques is discussed into detail, based on extensive research by the authors in the field. This is new, and we found some amazing lifts in areas such as credit card fraud detection and tax avoidance!
The book provides a sound mix of both theoretical and technical insights, as well as practical implementation details. Various real-life case studies and examples are used for further clarification. The book also comes with a course which we teach on the topic. We hope the reader will enjoy it and welcome any feedback and/or suggestions for improvement!