Module
Community Detection for Fraud
Fraud rarely happens in isolation. Organized fraud operates through coordinated networks—multiple actors sharing infrastructure, moving money, and hiding in plain sight.
In this module, you'll use graph algorithms to uncover these hidden networks and identify suspects who haven't been flagged yet.
You'll learn:
- How Full definition for Louvain algorithm (opens in a new tab)A community detection algorithm that repeatedly merges nodes into groups for as long as merging raises modularity. Full definition for community detection (opens in a new tab)A family of algorithms that group nodes by how they connect. Each algorithm defines a community differently. finds groups of densely connected Full definition for node (opens in a new tab)A vertex in a graph. In a property graph it can carry labels and properties.—and reduces your search space by 98%
- How Full definition for degree centrality (opens in a new tab)A score for each node equal to its number of outgoing relationships. identifies high-connection nodes to filter noise from your analysis
- How Full definition for weakly connected components (opens in a new tab)Groups of nodes in which every node is reachable from every other, once relationship direction is ignored. The GDS algorithm that finds them takes the same name. (WCC) provides deterministic, explainable community assignment
- How to encode domain hypotheses as graph Full definition for relationship (opens in a new tab)A named, directed connection between two nodes. Every relationship has a type, a start node and an end node. for targeted fraud detection
By the end of this module, you'll have identified 211 previously unknown fraud risk users who account for 13% of all Full definition for transaction (opens in a new tab)A unit of work that either succeeds in full or leaves no trace. volume—using algorithms that are simple by design but powerful when combined with domain knowledge.