ds-model-explainability

What problem does it solve?

Explainability and fairness in machine learning models, enabling you to communicate predictions, audit biases, and document behavior for stakeholders and regulators.

Core Features & Use Cases

• Global and local explanation capabilities for model predictions (SHAP, PDP/ICE, LIME).
• Fairness auditing and documentation via model cards and fairness metrics.
• Use Cases: regulatory reviews, deployment documentation, and product-ready explanations for customers.

Quick Start

Explain a given model prediction using SHAP values and provide a concise global model summary.