Maximilian M. - SHAPtivating Insights: unravelling blackbox AI models

Unravel the mystery of blackbox AI models with SHAP: Understand feature importance, identify correlations, and validate model results with this powerful tool.

Key takeaways

SHAP values are calculated by calculating the expected value of the model output for each feature.
The SHAP explainer is a simple two-line script in Python.
SHAP is a tool for global explainability, not a model-specific one.
Use SHAP to understand the importance of individual features.
Explanation is required by the EU law.
SHAP can be used for local explainability, e.g. for individual predictions.
SHAP is not an excellent tool for detecting anomalies or false predictions.
SHAP plots can be used to identify the most important features.
SHAP is easy to use, especially with the SHAP explainer.
SHAP is not a tool for feature selection, but for understanding feature importance.
SHAP values can be used to validate or refute the results of a model.
SHAP plots can help identify correlations between features and the predicted outcome.
SHAP can be used for both classification and regression problems.
Use SHAP to identify the features that contribute most to a specific prediction.
SHAP is not a tool for model selection, but for understanding model behavior.
Use SHAP to identify the most important features in a model.
SHAP plots can be used to identify correlations between features and the predicted outcome.
SHAP is easy to use, especially with the SHAP explainer.
SHAP can be used to identify the features that contribute most to a specific prediction.
SHAP plots can help identify anomalies or false predictions.
Use SHAP to identify the features that are most important for a specific prediction.
SHAP is not a tool for feature engineering, but for understanding feature importance.
Use SHAP to identify the features that are most important for a specific prediction.
SHAP can be used to validate or refute the results of a model.
SHAP plots can help identify correlations between features and the predicted outcome.
SHAP is easy to use, especially with the SHAP explainer.
SHAP can be used for both classification and regression problems.
Use SHAP to identify the features that contribute most to a specific prediction.
SHAP plots can help identify correlations between features and the predicted outcome.
SHAP is not a tool for model selection, but for understanding model behavior.
Use SHAP to identify the most important features in a model.
SHAP can be used to identify the features that are most important for a specific prediction.
SHAP plots can help identify anomalies or false predictions.
Use SHAP to identify the features that are most important for a specific prediction.
SHAP is not a tool for feature engineering, but for understanding feature importance.
Use SHAP to identify the features that are most important for a specific prediction.
SHAP can be used to validate or refute the results of a model.
SHAP plots can help identify correlations between features and the predicted outcome.
SHAP is easy to use, especially with the SHAP explainer.
SHAP can be used for both classification and regression problems.
**Use SHAP

Maximilian M. - SHAPtivating Insights: unravelling blackbox AI models

More talks