Explainability Mode

Explainability Mode is a feature of the Dark Matter algorithm available for enterprise accounts.

Explainability Mode allows users to track features through Dark Matter algorithm training, opening the door to feature observability, explainability, and importance. This can be utilized with any "out of the box" observability packages (e.g. shap), or using Ensemble AI's post processing functions for streamlined reporting.

Output Format

With Explainability Mode, the resulting output will be a Pandas DataFrame with the original input feature names as the columns but with the embedding values in place of the original input data.

Before transformation

Note: Dark Matter requires the number of features (input_column_size) to be explicitly defined.

input_column_size=5. Where do I assign this?

Original input features

After transformation

Note: Dark Matter will generate embeddings of the size specified (output_column_size).

output_column_size=5. Where do I assign this?

Output features using explainability mode