liveBook · Manning

Graph-based pattern discovery

As explained in Financial AI in Practice

An analytical technique that represents entities and their relationships as a graph to reveal patterns such as shared connections.

A chargeback investigation can miss coordinated activity when each transaction is examined alone. Graph-based pattern discovery instead views users, merchants, and their transactions as connected entities, making shared relationships easier to spot. section 7.4.1

Start with transaction records involving users who filed chargebacks. Map their connections to merchants, then inspect whether users share merchants or disputed transactions. A shared connection is a lead for investigation, not proof of fraud. section 7.4.1

Figure 7.5 A conceptual visualization of transactions involving users who filed chargebacks. This simplified graph highlights the ability to quickly identify commonly shared merchants among users. The numbers on the edges represent the transaction dates (YY.MM.DD format). The solid lines indicate normal transactions, while the dashed lines represent transactions that were later disputed as chargebacks. While this example remains intentionally minimal, such graph-based relationships become even more valuable in complex real-world scenarios where detecting shared connections can reveal fraud rings or coordinated behavior.
figure

The conceptual graph distinguishes ordinary transactions from later-disputed ones and labels transaction dates, making shared merchants visible. section 7.4.1

How Financial AI in Practice covers it

How deep it goes
Defines the graph perspective and illustrates it conceptually, deferring advanced graph neural network mathematics.
Examples
Uses users who filed chargebacks, their shared merchants, dated transaction edges, and distinct markings for later-disputed transactions.
What it assumes
Assumes transaction and chargeback records but introduces the network perspective without requiring advanced graph neural network mathematics.
What you can do after
Evaluate/understand it by spotting shared connections that warrant further fraud investigation.
How it connects
Connects chargeback fraud and fraud rings to transaction relationships, contrasting this perspective with individual-transaction rules and graph neural networks.

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Financial AI in Practice. The section links point to the parts of the book it draws on.