Confidential Payments Client - Fraud Risk Scoring (KSA).

The platform needed instant onboarding decisions while also maintaining a separate continuous-monitoring view of account behavior over time.

The behavioral model had to leverage both unlabeled anomaly signals and historical confirmed fraud without exploding false positives on sparse or shifting populations.

I built a real-time onboarding scorer using customer profile, document, device, IP, geolocation, channel, and early behavioral signals to return a risk score and three-way decision into the middleware layer.

For ongoing risk monitoring, I designed a semi-supervised architecture where Isolation Forest first measured account abnormality, then fed that continuous anomaly score into an XGBoost classifier alongside 50+ engineered features derived across micro, short, medium, and baseline windows.

To keep the system reliable in production, I added non-sufficient-data routing, cohort-aware standardization, PSI-based drift checks, Platt-scaled calibration, and SHAP attribution for Medium and High-risk accounts before both models were exposed to SFM through REST API middleware.