Fraud can be a major source of cost and disruption for your organization. Observing, tracking, inspecting, and analyzing behaviors needs to be done across multiple channels (customers, employees, vendors) to identify the right and wrong trends and understand where intervention should be applied. Understanding where vulnerabilities exist and closing them through at-scale analysis reduces the risk of fraud.
AWS Services
Purpose-built cloud products
![](https://d1.awsstatic.com/Gradient-Divider-orange-blue.317b0a6e1db69aa03ede8c5fd6fad7ee117a626f.jpg)
Total results: 2
- Alphabetical (A->Z)
Guidance
Prescriptive architectural diagrams, sample code, and technical content
![](https://d1.awsstatic.com/Gradient-Divider-orange-blue.317b0a6e1db69aa03ede8c5fd6fad7ee117a626f.jpg)
Total results: 3
- Publish Date
-
Near Real-Time Fraud Detection with Graph Neural Network on…
This guidance solution demonstrates an end-to-end, near real-time anti-fraud system based on deep learning graph neural networks. This blueprint architecture uses graph databases to construct a heterogeneous graph from tabular data and train a Graph Neural Network (GNN) model to detect fraudulent transactions.