Page tree
Skip to end of metadata
Go to start of metadata
  • Help Content has moved. Help documentation for Marketing Cloud Personalization is now published in Salesforce Help. Starting February 1, 2023, the site will no longer be available.
  • New Name: Interaction Studio (formerly Evergage) is now known as Marketing Cloud Personalization. The new name reflects our mission and vision for innovation in Salesforce Marketing Cloud. We wish we could snap our fingers to update the name everywhere, but you can expect to see the previous name in various places until we replace it.  

Einstein Decisions provides robust reports as a product of our continuous model training. Each time the model is trained, which typically occurs multiple times per week, a report is generated and saved within Interaction Studio. This reporting provides your analytics and data science resources with additional insight into how and why the algorithm is making its decisions. It does not replace the promotion stats and campaign stats screens that your business users are already leveraging. These screens will still be used to track and understand campaign and promotion performance.

This Article Explains

Einstein Reports is broken down into five key sections: Content Zone Description, Training Data, Historical Performance, Training, and Deployment. This article outlines the types of data that you will find in each section of the reports and highlights some tips and best practices for each.

Sections in this Article

Accessing Einstein Reports

  1. Log into Interaction Studio 
  2. In Machine Learning, select Einstein Reports
  3. Select the Report Type, which is based on the content zone or channel
  4. Click View to view the training report, or Download to save an HTML copy of it to your computer

Note: Einstein Reports are likely best reviewed/consumed by an analytics or data science resource.

Content Zone Description

Each Einstein Decisions training is for a single content zone or tag. Content zones and tags group promotion assets that are served in a specific location or manner (zone). Additional information on configuring content zones or tags on promotion assets is available here. This section of the report describes the content zone or tag that is currently being trained and lists the promotions that have assets with this zone or tag assigned.

Training Data

A quick summary of the data that has been collected. This gives you a window into both how active Einstein Decisions has been and how much training data it now has to work with.

Historical Performance

This section describes how well your promotions achieved their purpose, and how effective they are overall, if they were served without machine learning driven personalization.

Model Training

Einstein Decisions trains several candidate machine learning models from your data, and checks them against each other to determine the model that will provide the most business value as defined by your training target.

Model Deployment

Once a model is selected from the previous model training step, your model is deployed and set live.The selected model is recorded here.

  • No labels