# Unlocking the relational power of graph neural networks in fraud prevention

DevFeed: [Unlocking the relational power of graph neural networks in fraud prevention](<https://devfeed.tech/articles/unlocking-the-relational-power-of-graph-neural-networks-in-fraud-prevention-56967.md>)

Original publisher: [Read original article](<https://www.thoughtworks.com/insights/articles/graph-neural-networks-in-fraud-prevention>)

Author: Alla Gancz, Artiom Troyanovsky, Joao Salcedo, Brian Blanchard, Paul Chang, Georgios Kolovos: Payments and FinTech Leader, Shardul Vaidya, Md Naim, Zachary Jacobson

Published: 2026-03-16T00:00:00Z

Content type: article

Language: en

Sources: [Thoughtworks Insights](<https://devfeed.tech/sources/thoughtworks-insights.md>)

Topics: [Graphs](<https://devfeed.tech/topics/graphs.md>), [Payment Fraud](<https://devfeed.tech/topics/payment-fraud.md>), [Deep neural networks](<https://devfeed.tech/topics/deep-neural-networks.md>), [Machine learning](<https://devfeed.tech/topics/machine-learning.md>), [Inference](<https://devfeed.tech/topics/inference.md>), [real-time](<https://devfeed.tech/topics/real-time.md>), [Transactions](<https://devfeed.tech/topics/transactions.md>), [Security, Privacy and Abuse Prevention](<https://devfeed.tech/topics/security-privacy-and-abuse-prevention.md>)

Tags: [ai-and-ml](<https://devfeed.tech/tags/ai-and-ml.md>), [false-positives](<https://devfeed.tech/tags/false-positives.md>), [financial-services](<https://devfeed.tech/tags/financial-services.md>), [fraud-detection](<https://devfeed.tech/tags/fraud-detection.md>), [graph](<https://devfeed.tech/tags/graph.md>), [inference](<https://devfeed.tech/tags/inference.md>), [low-latency](<https://devfeed.tech/tags/low-latency.md>), [machine-learning](<https://devfeed.tech/tags/machine-learning.md>), [neural-networks](<https://devfeed.tech/tags/neural-networks.md>), [payment-fraud](<https://devfeed.tech/tags/payment-fraud.md>), [payment-systems](<https://devfeed.tech/tags/payment-systems.md>), [security](<https://devfeed.tech/tags/security.md>)

## AI overview

This article describes a fraud-prevention approach that combines graph-based intelligence, neural networks, and AI inference pipelines for real-time payment systems. It explains how payment fraud has evolved from rules-based detection to machine-learning and behavioral approaches, with particular attention to authorized push payment scams and the need for low-latency, explainable detection.

## Source excerpt

Unlocking the relational power of graph neural networks in fraud prevention