chapter eight

8 Basic approaches to graph-powered fraud detection

 

This chapter covers

  • An introduction to different types of fraud in different domains
  • The role of graphs in modeling data for revealing frauds faster and more easily
  • Some techniques and algorithms for fighting fraud using a simple graph model

Fraud is an uncommon, well-considered, time-evolving, carefully organized and imperceptibly concealed crime that appears in many different types and forms.

According to Van Vlasselaer et al. [2017]:

This definition highlights six characteristics of fraud that are associated with the challenges related to developing a fraud-detection system:

8.1   Fraud prevention and detection

8.2   The role of graphs in fighting fraud

8.3   Warm-up: The basic approaches

8.3.1   Finding the origin point of credit card fraud

8.3.2   Identifying a fraud ring

8.3.3   Advantages of the graph approach

8.4   Summary

8.5   References