You are here:
Evaluate Model Quality
Model performance metrics reveal quality measures and associated details for a model. Use model performance to evaluate a model's ability to predict an outcome. When ready, you then deploy a model to Salesforce to predict outcomes in production.
Note Einstein Discovery stories are now models. We wish we could snap our fingers to update
the name everywhere, but you can expect to see the previous name in a few places until we
replace it.
To view model performance, on the Model sidebar, click Performance. The metrics that are visible in Performance depend on the use case (binary classification, numeric, or multiclass classification) for the outcome variable in your model.
- Metrics for Numeric Use Cases
The numeric use case is based on outcomes that are numeric variables. Model Performance shows quality statistics associated with linear regression models. - Metrics for Binary Classification Use Cases
The binary classification use case is based on text (categorical) variables with binary outcomes. Model Performance shows quality statistics associated with logistic regression models. - Metrics for Multiclass Classification Use Cases
The multiclass classification use case is based on categorical variables with 3–10 possible outcomes. The Model Metrics tabs show quality statistics associated with multiclass models.
Did this article solve your issue?
Let us know so we can improve!
