Explainability

Explain predictions to enhance model transparency, ensure ethical and unbiased outcomes, and gain insights into the underlying data patterns.

Explain a prediction

We assume that you have deployed a model with an explainer. Use the UI, Deeploy API, or Python client to explain a prediction.

UI

(SHAP Kernel explainer only) Navigate to the Predictions tab in your Deployment.

Click Explain to generate an explainer for any prediction that was made the current commit.

Deeploy API

Consult the inference section within the Swagger documentation

Python

Consult the predictions and explanations section within the Python client documentation