Manage and Deploy Models in Einstein Discovery

Einstein Discovery uses models to predict outcomes and suggest ways in which to improve predicted outcomes. You can evaluate model quality and compare models before you deploy and manage them.

• About Models
  A model is the sophisticated, custom mathematical construct that Einstein Discovery uses to predict a particular outcome. A model accepts inputs (one or more explanatory variables) and produces outputs (a predicted outcome, top factors, and improvements). Create a model and Einstein Discovery generates the predictive and prescriptive analytics.
• 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.
• Compare Models
  Compare metrics for multiple models side by side to see how they stack up against each other. For example, comparing segments in your data can reveal the most important variables in each segment.
• Deploy Models
  Deploy a model so that you can use it to make predictions and improvements.
• Manage Prediction Definitions and Models
  Use the Model Manager to view, configure, and manage prediction definitions and models that have been deployed in your org.