Shivam.
Open to roles
Data Strategy Consultant · Simon Vision Consulting · Oct to Dec 2024

City of Rochester

XGBoostSHAPPythonExplainable AI
62 73%Model accuracy
Per-flagPlain-English reason

The short version

An explainable fraud-detection model for the City of Rochester. XGBoost + SHAP lifted accuracy from 62% to 73% — and every flag ships with a one-line reason, so loan officers can act on it instead of second-guessing it.

The full story

The City of Rochester had a fraud model at 62% accuracy that nobody trusted. When it flagged a case, the loan officers couldn’t tell why — so they second-guessed every decision.

What I built

An explainable fraud-detection model using XGBoost, with SHAP for explainability. Accuracy went from 62% to 73% — but the bigger win was that every flagged case came with a one-line explanation of which features drove the score.

Why it mattered

The officers stopped second-guessing, because they could finally see the evidence. That’s the point I keep coming back to: in production ML, the accuracy lift only matters if the people using it can act on it.

The model supports the humans making the call. It doesn’t replace their judgment — it shows its work so they can trust it.

Stack

Python, XGBoost, SHAP. Delivered through Simon Vision Consulting for the City of Rochester.

Next case studySixPoint AI