Explainable Credit Scoring in the Browser
Browser-based gradient-boosted credit scoring that advises, while the credit officer decides.
Key results
In-browser
Client-side scoring using ONNX Runtime Web
- Sole engineer
- May 2026 to Sep 2026
- Regional lender
- Project
- L3:credit-scoring-poc
Results
In-browser
Client-side scoring using ONNX Runtime Web
Problem
The credit team needed quick, explainable scoring advice while keeping applicant data out of server-side models.
Contribution
- I trained an XGBoost model, compared it with LightGBM and random forest, and exported it for ONNX Runtime Web.
- I combined model output with deterministic policy rules and manual-review flags. Scoring remains advisory; the credit officer decides.
Gallery
Tech stack
LightGBM
ONNX Runtime Web
Next.js- XGBoost
More AI Engineering projects
Technical Consultant, Software & AI, Metrodata (PT Mitra Integrasi Informatika)