The Einstein Attribution model is based on a concept borrowed from cooperative game
theory called the Shapley Value. The Shapley Value calculates the contribution of each player in
a cooperative game, where players use different skill sets to achieve a collective reward. We
adapt this method for marketing attribution by distributing an opportunity amount among the
campaigns that are associated with the opportunity.
Required Editions
Available in: Account Engagement Advanced and Premium
Editions with Salesforce Enterprise, Performance, or Unlimited
Edition
Einstein uses your historical data to identify common journeys that users take. It scans a
collection of campaigns that influenced an opportunity and assigns a marginal contribution
amount to each touchpoint. The model averages that amount across every possible sequence of
touchpoints. This sequencing allows the model to identify a more accurate contribution amount,
instead of just reiterating a touchpoint’s position in the journey.
Analyzing Touchpoints
Touchpoints include tracked engagement activities on an Account Engagement prospect or a
Sales Cloud campaign member. An engagement activity is one that represents a person’s
interest, for example an email open, email click, form submission, or event attendance.
Campaign members whose status is Responded are included in the model. However, since
attribution also uses Account Engagement visitor activities in its calculations, it’s
possible for records to appear in reports whose status isn’t Responded. The report doesn’t
contain Account Engagement activities that are tracked but that don’t indicate engagement,
such as invitations and sent emails.
Associating Campaigns
Sales Cloud often uses the Opportunity Contact Role to link campaigns and opportunities.
However, users don’t always create this reference, which means you don’t get all the
campaign attribution data you need.
To fill this gap, Einstein Attribution creates virtual opportunity contact roles for use in
its models. We analyze tasks, emails, and events on your opportunities, and then we extract
the contacts who are involved in them. If that isn’t sufficient, we extrapolate
relationships via a prospect’s email domain. These methods reveal more relationships and
provide more data, but you don’t have to change anything.
Note Although Einstein Attribution works with Campaign Influence object, the attribution
model doesn’t use any auto-association rules that have been set up.
Tuning the Model
Two tuning settings are available to help you align Einstein Attribution to your business:
time frame and success milestone. By default, the model scans campaign and opportunity
relationships up to 6 months prior to opportunity creation.
With time frame, you identify the period to track prospect and campaign member activities.
The success milestone setting allows you to choose an active opportunity stage, which
indicates that an opportunity is successful, or converted. The Data-Driven Model considers
all journeys that reached that success milestone and identifies the contribution of each
campaign along the way.
Example To find out what’s most effective in encouraging annual renewals, you might set the
time frame to 12 months and select a custom stage, such as Renewed.
Did this article solve your issue?
Let us know so we can improve!
Loading
Salesforce Help | Article
Cookie Consent Manager
General Information
Required Cookies
Functional Cookies
Advertising Cookies
General Information
We use three kinds of cookies on our websites: required, functional, and advertising. You can choose whether functional and advertising cookies apply. Click on the different cookie categories to find out more about each category and to change the default settings.
Privacy Statement
Required Cookies
Always Active
Required cookies are necessary for basic website functionality. Some examples include: session cookies needed to transmit the website, authentication cookies, and security cookies.
Functional Cookies
Functional cookies enhance functions, performance, and services on the website. Some examples include: cookies used to analyze site traffic, cookies used for market research, and cookies used to display advertising that is not directed to a particular individual.
Advertising Cookies
Advertising cookies track activity across websites in order to understand a viewer’s interests, and direct them specific marketing. Some examples include: cookies used for remarketing, or interest-based advertising.