8 Basic approaches to graph-powered fraud detection
This chapter covers
- An introduction to types of fraud in different domains
- The role of graphs in modeling data to reveal frauds faster and more easily
- Using a simple graph model to fight fraud
According to Van Vlasselaer et al. [2017]:
Fraud is an uncommon, well-considered, time-evolving, carefully organized and imperceptibly concealed crime that appears in many different types and forms.
This definition highlights six characteristics of fraud that are associated with the challenges related to developing a fraud detection system:
-
Uncommon—In almost all types of fraud and across domains, only a minimal portion of the data available is related to (or recognized to be related to) fraud. Detecting ...
Get Graph-Powered Machine Learning now with the O’Reilly learning platform.
O’Reilly members experience books, live events, courses curated by job role, and more from O’Reilly and nearly 200 top publishers.
