XAI View Component with a Custom Model

This application is a simple example of Xgboost model with KNIME Software for binary and multiclass classification. The model output is then explained via the interactive XAI View. Machine Learning Interpretability (MLI) techniques used: SHAP explanations/reason codes, partial dependence, individual conditional expectation (ICE) curves and a surrogate decision tree.

The workflow also works locally on KNIME Analytics Platform. Make sure to use "Apply and Close" in bottom-right corner of each view.

External resources

• Explainable artificial intelligence - WIkipedia
• Interpretable Machine Learning - Christoph Molnar - 2020-09-28
• XAI View Component - KNIME Hub
• KNIME Integrated Deployment - KNIME.com