Fraud investigators have at their disposal large datasets that hold the clues to detecting fraud. These clues are left behind by criminals who try to hide their activity behind layers of more or less intricate schemes. To uncover illegal activities, investigators have to connect the pieces of the puzzle to discover evidence of wrongdoing.
Most anti-fraud solutions are able to connect simple data points together to detect suspicious behaviors: an IP address to a user, transaction activities to a place of residence, or a loan request history to a client.
But these applications fall short on more complex analysis that would imply several levels of relationships or data types. This is mostly because technology on which these applications often rely create data silos. The relational databases that emerged in the ’80s are efficient at storing and analyzing tabular data but their underlying data model makes it difficult to connect data scattered across multiple tables to understand networks.
Graph databases are designed for this purpose. Their data model is particularly well suited to store and to organize data where connections are as important as individual data points. Connections are stored and indexed as first-class citizens, making it an interesting model for investigations in which you need to understand relationships.
In this article, we review three common fraud schemes and see how a graph approach can help investigators detect them faster and more efficiently.