Using Campaign, you can optimize the design and delivery of customer journeys to predict each individual’s engagement preference. Powered by Journey AI, Adobe Campaign can analyze and predict open rates, optimal send times, and probable churn based on historical engagement metrics.
Machine learning models
Adobe Campaign Standard offers two new Machine Learning models: Predictive Send Time Optimizations and Predictive Engagement Scoring. These two models are together referred to Journey AI which is a class of machine learning models that are specific to designing and delivering better customer journeys.
Predictive send time optimization: Predictive send time optimization predicts which is the best send time for each recipient profile for email opens or clicks. For each recipient profile, the scores indicate the best send time for each weekday and which weekday is the best to send for best results.
Predictive engagement scoring: Predictive engagement scoring predicts the probability of a recipient engaging with a message as well as the probability of opting out (unsubscribing) within the next 7 days after the next email send. The probabilities are further divided into buckets according to the specific risk of disengagement, medium, or low. Along these the model also provides the risk percentile rank for the customers to understand where the rank of a certain customer in relation to others.
This capability is not available out of the box as part of the product. The implementation requires Adobe Consulting to be engaged. Please reach out to your Adobe representative to find out more.
The feature requires the usage of an Azure or Amazon S3 storage that must be provided by the customer.
Predictive send time optimization predicts which is the best send time for each recipient profile for email opens and clicks. For each recipient profile, the scores indicate the best send time for each weekday and which weekday is the best to send for best results.
Within the Predictive Send Time Optimization model, there are two sub-models:
Model input: Delivery logs, tracking logs and profile attributes (non-PII)
Model output: Best time to send a message (for opens and clicks)
Output details
These predictive capabilities only apply to email deliveries.
The model needs at least one month of data to produce significant results.
Once implemented into Campaign, Machine Learning capabilities enrich profiles data with new tabs with their best open/click scores. The metrics are computed by Journey AI and they are brought into Campaign using technical workflows.
To access those metrics, you need to:
Open a profile and click the Edit button.
Click the Send Time Score By Click or Send Time Score By Open tab.
By default, the profile scores will give the best time of the day for each day of the week and the best overall time in the week.
In order for the emails to go out at the optimal time per profile, the delivery must be scheduled using the option Send at a custom date defined by a formula.
Learn how to compute the sending date in this section.
The formula needs to be populated with the specific best time of the particular day when the delivery will go out.
Formula example:
AddHours([currentDelivery/scheduling/@contactDate],
[cusSendTimeScoreByClickprofile_link/@EMAIL_BEST_TIME_TO_CLICK_WEDNESDAY])
The data model might be different depending on your implementation.
The predictive engagement scoring lets you:
This model uses multiple scores to indicate:
These predictive capabilities only apply to email deliveries.
The model needs at least one month of data to produce significant results.
Model Input: Delivery logs, tracking logs and specific profile attributes
Model Output: A profile attribute that describes the profile’s score and category
To access those metrics, you need to:
Open a profile and click the Edit button.
Click the Engagement Scores for Email Channel tab.
By using a query activity in a workflow, you can use the score to optimize your audience.
For example, with the Retention level criteria: