scikit-learn compatible tools for building credit risk acceptance models
Automatic optimal discretization pipeline
Monotone Weight Of Evidence Transformer and LogisticRegression model with scikit-learn API
The Galaxy framework is Rely.io's integration solution, enabling simple connections to third-party APIs. Built in Python, it features reusable components and uses JQ syntax to map retrieved data into the Rely data model.
Score model outputs against explicit rubrics with an Azure-backed judge, deterministic aggregation, and diffable JSON reports.
Public-safe demo of the Gauges Green AI harness for senior operators
Founder-facing hiring and talent pipeline operating system.
Interpretable credit-scoring studio: an end-to-end PD scorecard engine (WoE + MIP-optimal binning + elastic-net logistic regression, tuned with Optuna) that turns raw bureau data into a points-based, regulator-friendly scorecard — with full diagnostics (KS/AUC/Gini), Excel/visual exports, and a Streamlit UI.
Add a description, image, and links to the scorecards topic page so that developers can more easily learn about it.
To associate your repository with the scorecards topic, visit your repo's landing page and select "manage topics."