Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
March 26, 2026
·
São Paulo
Graph-Enhanced XGBoost: Beating Fraud Detection Baselines with Neo4j
Discover how graph features from Neo4j, combined with XGBoost, significantly improve fraud detection by revealing hidden connections invisible in tabular data.
Overview
A graph-based financial fraud detection system built on Neo4j, using the IEEE-CIS dataset to model transactions, cards, devices, emails, and addresses as a connected network — and combining graph features with XGBoost to significantly outperform traditional tabular models.
Links
Tech stack