Home / Projects / The Fraud Detective
DATA SCIENCE & AI · INTERNATIONAL

Paste a transaction, see if it's a red flag.

Synthetic training data

Problem Statement

Research question: Can a model distinguish fraudulent transactions from legitimate ones using account-relative behavioral signals — without relying on the raw transaction amount alone?

Banks lose billions annually to fraud that static, rule-based systems catch too late. This project builds a classifier that scores each transaction using signals relative to the account's own history — amount, timing, velocity, distance, merchant familiarity — tuned toward catching more fraud at the cost of some false alarms.

70.9%
Precision
96.0%
Recall
0.997
ROC-AUC

Try it live

Runs on Hugging Face Spaces
Waking up the model — this can take up to a minute on the first visit today. It'll be instant after that.

How this works

A Random Forest classifier trained on 60,000 synthetic transactions, deliberately built with realistic class overlap. An earlier version scored a suspicious 100% across every metric — a sign of an unrealistic pattern, fixed by adding genuine overlap.

What it gets right

Catches 96% of fraud in testing, appropriate for a screening tool meant to flag for human review. Every flagged transaction lists the specific signals that drove the score.