The model in this card analyzes each contact’s engagement record to determine the optimal frequency at which to send email or MobilePush messages to that contact.
- Model Details
The Einstein Engagement Frequency model in Marketing Cloud Engagement optimizes the frequency of customer engagement with email content and MobilePush using these training algorithms, parameters, fairness constraints, and features. - Intended Use
The Einstein Engagement Frequency model in Marketing Cloud Engagement is intended for these use cases. - Relevant Factors
These factors are associated with the Einstein Engagement Frequency model Marketing Cloud Engagement. - Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance measures are associated with the Einstein Engagement Frequency model. - Training Data
You have a customized version of the model that’s trained on your data alone. Data from one Salesforce customer doesn’t affect the behavior for another Salesforce customer. While model training happens for each customer on their data, the initial development of the model is validated with a representative set of pilot customers’ data. - Ethical Considerations
Review ethical factors associated with the Einstein Engagement Frequency model in Marketing Cloud Engagement. To avoid bias and other ethical risks, the Einstein Engagement Frequency model doesn’t include demographic data. - Refresh Cadence
Review the refresh cadence associated with the Einstein Email Engagement Frequency model in Marketing Cloud Engagement.
Model Details
The Einstein Engagement Frequency model in Marketing Cloud Engagement optimizes the frequency of customer engagement with email content and MobilePush using these training algorithms, parameters, fairness constraints, and features.
Person or Organization
Salesforce Einstein for Marketing Cloud Engagement
Model Date and Version
- May 2020
- Minor changes can occur throughout the release
- Major changes can occur and are communicated via release notes
Model Type
Matrix factorization, Recommendation system
General Information
Einstein Engagement Frequency (EEF) helps marketers determine the right number of emails and MobilePush messages to send to individual subscribers of an organization, reducing the unsubscribes that result from message fatigue. Marketers can use EEF to identify opportunities to further engage subscribers with emails. The model analyzes individual subscribers’ historical engagement patterns over different frequencies. And it uses data of other users with similar patterns to help complete and adjust the scoring of each frequency. The ideal frequency range of each individual is then calculated based on those scores to help find the best frequency band that maximizes engagement. Salesforce trains each customer’s model using only that customer’s data.
Constraints
- A minimum of 10 subscribers is required to model for engagement frequency.
- A minimum of five frequencies is required to model for engagement frequency. The audience in your business unit must receive at least five variants of your messaging over a 28-day period. For EEF, a variant is defined as a message sending pattern, which is sending messages to subscribers with at least five different intervals.
License
Einstein Engagement Frequency is available to Marketing Cloud Engagement customers with any of these editions.
- Corporate Edition
- Enterprise Edition
- Enterprise+ Edition
Intended Use
The Einstein Engagement Frequency model in Marketing Cloud Engagement is intended for these use cases.
Primary Intended Uses
The Einstein Engagement Frequency model powers the Frequency split activity in Journey Builder. The Frequency split activity is designed for marketing professionals to send the optimal number of emails to every subscriber in their business unit, reducing subscriber email fatigue. The feature predicts the optimal number of emails to send an individual contact, maximizing their engagement rate across all campaigns and message types, within a business unit.
Out-of-Scope Use Cases
Anything other than the primary use case is out of scope and not recommended. For example, prioritizing which messages to send to subscribers based on their current saturation level, and manually capping the send frequency per campaign, aren’t intended use cases.
Relevant Factors
These factors are associated with the Einstein Engagement Frequency model Marketing Cloud Engagement.
Model Input
Einstein Engagement Frequency analyzes up to 90 days of historical engagement patterns of the subscribers. The engagement history includes these factors.
- Email sends, bounces, and engagement events including open, click, and unsubscribe, spam complaints, and associated timestamps
- Data and metadata about customer sending patterns, including how campaigns are executed
The engagement history that Einstein Engagement Frequency analyzes excludes these factors.
- Data purchased or collected from third parties
- Demographic Data, which is typically stored in SFMC as data extensions or subscriber or contact attributes
- Specific content within the email template or rendered email body
Model Output
- A personalized frequency band for each active subscriber and an overall Business Unit–level ideal frequency band for email
- A personalized frequency band for each active subscriber and an overall app-level ideal frequency band for MobilePush
Groups
The model doesn’t include demographic data or other data purchased from third-party data providers. The model uses engagement data such as opens, sends, and patterns.
Environment
The model is trained and deployed in the Marketing Cloud Engagement environment.
Metrics
Einstein evaluates and monitors model performance metrics to ensure and improve the quality of the model. These performance measures are associated with the Einstein Engagement Frequency model.
Model Performance Measures
Model performance metrics include metrics like the spread and sparsity of input metrics and the correlation of output scores to historical observations. All metrics are aggregated and anonymized.
Training Data
You have a customized version of the model that’s trained on your data alone. Data from one Salesforce customer doesn’t affect the behavior for another Salesforce customer. While model training happens for each customer on their data, the initial development of the model is validated with a representative set of pilot customers’ data.
Ethical Considerations
Review ethical factors associated with the Einstein Engagement Frequency model in Marketing Cloud Engagement. To avoid bias and other ethical risks, the Einstein Engagement Frequency model doesn’t include demographic data.
Refresh Cadence
Review the refresh cadence associated with the Einstein Email Engagement Frequency model in Marketing Cloud Engagement.
Scores and Models
Einstein Engagement Frequency scores and models for email are updated weekly. The refresh cadence varies by one to several days based on a customer's individual business unit.