← 🤖 Machine Learning

💳 Fraud Scoring Engine

Precision:
Recall:
F1 score:
Blocked / Approved: 0 / 0
Scoring latency: — ms
FPS:
Drag — rotate · Scroll — zoom

💳 Real-Time Fraud Detection Scoring Lab

A 3D feature-space view of a gradient-boosted fraud classifier: historical transactions cluster as legitimate or fraudulent points, a movable decision plane marks the current probability threshold, and live transactions stream through, get scored, and route to an approved or blocked gate.

🔬 What It Demonstrates

Moving the decision threshold slides the boundary plane along the axis between the legitimate and fraud clusters, directly trading recall for precision — exactly the tuning fraud teams do in production.

🎮 How to Use

Adjust the threshold, stream rate, base fraud rate and model separability, then watch precision/recall update and transactions get routed to the APPROVED or BLOCKED gate in real time. Toggle explainability bars to see each transaction's feature contributions.

💡 Did You Know?

Because genuine fraud is rare, a model that flags nothing can still be "99% accurate" — real systems are judged on precision, recall and F1, not raw accuracy, and the threshold is a live business dial tuned against cost of fraud versus customer friction.