2

Salesforce marketing cloud has recently released a new feature Einstein send time optimization. Basically, SFMC calculates the best time to send an email at each subscriber level based on their email open history.

How does it calculates send time for subscribers which are newly added and don't have any email send or open history? Does it send them right away or there is some optimum send time at an overall level as well which can be used in such cases.

  • Since it is a feature that has been added only a couple of days ago, i believe you will not find additional information or practical information about this feature until some users begin to implement and test with it. Since this feature involves signing a contract and time to implement for salesforce it will most likely be better to ask support directly. I created a support case for it -> i will share the answer. Did you already create a support case? – Johannes Schapdick Jun 26 at 6:45
1

Here the answer from Support:

In regards to how it calculates send time for subscribers which are newly added and don't have any email send or open history, it won't send to them straight away. Einstein gathers data for approximately 20 factors, such as the number of emails sent to a contact, the number of emails a contact opened, and the day of the week the email is opened. It uses machine-learning to weight each factor according to its level influence on predicting future engagement behaviour. Then Einstein analyzes this data and assigns a likelihood score to each of the 168 hours in a week for each contact. Send Time Optimization uses this information to recommend the best send times for each contact.

I will continue asking about more details because i think the answer is not complete. You can leave comments under this answer for the remaining questions you have. I will transfer them to the case I opened.

0

If an subscriber does not have a score they will move immediately through the STO activity to the email activity.

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.