A fraud detector designed around the cost of being wrong.

01 / The problem

Fraud made up less than 0.2% of the transaction data. That imbalance made overall accuracy nearly useless. The useful question was whether the model could catch fraud while keeping manual review manageable.

A model can look excellent by predicting every transaction as legitimate. I needed evaluation that reflected the cost of missed fraud and the operational cost of false positives.

02 / The approach

Build the evaluation around the decision.

1. 01

   Cleaned and standardized the anonymized transaction features.

2. 02

   Used five-fold cross-validation with F1 as the primary metric.

3. 03

   Trained a Random Forest and reviewed precision, recall, ROC-AUC, and the confusion matrix together.

4. 04

   Compared decision thresholds based on the review burden they would create.

03 / The result

The model score was only the start. The threshold determines how risk policy becomes day-to-day review work, so it should be chosen with the people handling the alerts.