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.

1
  • 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? Commented Jun 26, 2019 at 6:45

3 Answers 3

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.

1

In August 2022 someone posted as an answer a few bullet points from Salesforce documentation, but they did not provide a link or give attribution (i.e., plagiarism) nor did they put the answer in a quote block or give any other indication that it was not their original material. Almost two months after a request for them to remedy those issues, they did not; therefore the community deleted the answer.

I am unfamiliar with this content area, but in case that Salesforce documentation information is helpful/relevant (please comment under this answer if you are knowledgeable in this area and think it is not helpful/relevant), I am recreating that answer with a link and attribution.


From Einstein Send Time Optimization Model Details (https://help.salesforce.com/s/articleView?id=sf.mc_anb_einstein_sto_model_details.htm&type=5) Salesforce documentation:

A subscriber who doesn’t have at least one engagement event in the past 90 days is designated as pending a personalized send time. The model sends to these subscribers according to the Insufficient Data option that their admin selects in Setup.

  • The Send at Einstein’s optimal default time option means that Einstein aggregates scores for all of your subscribers that have sufficient data, creating a distribution of scores for every hour. Einstein STO then uses this distribution to assign scores randomly to subscribers who lack sufficient data. Such a subscriber can be assigned any optimal default time, but they’re more likely to be assigned an optimal default time that has a higher score than one that has a lower score. Randomization prevents each subscriber that’s pending a personalized send time from receiving an email at the same time, which helps avoid sending spikes and helps Einstein STO get better data.
  • The Send immediately option means that subscribers who are pending a personalized send time are sent an email immediately when they reach the STO activity.
  • Subscribers with adequate data are assigned a personalized send time. The model sends at one of the top three hours for each subscriber. Einstein STO randomly selects a single hour to send according to the distribution of the top three scores. Randomization allows Einstein STO to constantly monitor which hours can be better for sending and improve send time selection.
0

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

You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .