Loading
Salesforce now sends email only from verified domains. Read More
Market to Your Customers with Account Engagement
Table of Contents
Filter by (0)Add
Select Filters

          No results
          No results
          Here are some search tips

          Check the spelling of your keywords.
          Use more general search terms.
          Select fewer filters to broaden your search.

            Search all of Salesforce Help
            Search all of Salesforce Help
            How Behavior Scoring Works

            You are here:

            1. Salesforce Help
            2. Docs
            3. Marketing Cloud Account Engagement

            How Behavior Scoring Works

            Einstein Behavior Scoring uses machine learning to uncover the most influential behavior signals across past and current prospect engagement. For each prospect, Einstein considers all types of prospect engagement activities, and identifies positive and negative interactions. An evolving Einstein scoring model weights each activity and assigns a score from 0 through 100.

            Required Editions

            Available in: Account Engagement Advanced Edition with Salesforce Enterprise, Performance, or Unlimited Editions

            After you turn on Einstein Behavior Scoring, the model learns from the prospect activities and relationships it finds in your data. Prospects associated with opportunities that are created before you enable Behavior Scoring or that occur during the initial training period aren’t scored.

            Behavior Scoring uses your prospects’ engagement pattern data to improve the model over time. Frequency and recency are important factors, which are weighted and defined by activity type and asset. For example, the model could determine that an email open from last week more heavily impacts a prospect’s score than a form submission from 90 days ago.

            The model marks a prospect as converted when it’s linked to an opportunity, and is no longer scored. This conversion is determined in three ways.

            • A prospect’s associated lead or contact is linked to an opportunity.
            • A prospect’s associated contact is used as an opportunity contact role.
            • A prospect’s lifecycle stage becomes Sales Qualified Lead.

            Data Requirements

            Einstein Behavior Scoring uses various data to develop its model. From Account Engagement, the model considers visitor activity, prospect lifecycle stage, and lifecycle history. From Salesforce, it analyzes the opportunity contact role and the lead and contact records that are connected to prospects.

            When you first start set up Salesforce and Behavior Scoring, we use a baseline model. As you accumulate prospect engagement data, the model finds more patterns in your specific prospects and assets. To see these more tailored insights, your org must meet the following criteria.

            • Six months of engagement data for connected prospects.
            • At least 20 prospects linked to opportunities (determined by lifecycle stage or opportunity contact role).

            Locations

            • The Behavior Scoring Lightning component is available on lead and contact pages.
            • The Einstein Behavior Scoring dashboard is available in the B2B Marketing Analytics app.

            Rationales

            In addition to providing a score, Einstein also surfaces what we call rationales. A rationale is a positive or negative statement that tells you more about why the prospect scored the way they did. For example, clicking a social post is typically positive, but doesn’t necessarily mean that someone is ready to buy. Weight and sentiment can vary widely and the model changes along with your prospects’ buying patterns. Here are a few more examples of the types of activities you can expect to see in rationales.

            • Email opens
            • File, form, video views
            • Event registrations and check-ins
            • Unsubscribes and resubscribes
            • Spam complaints
             
            Loading
            Salesforce Help | Article