pilot-icon – This feature is currently on Pilot release for a limited number of clients only. If you are interested in participating in the pilot phase, please contact Emarsys Support.

Contents

What is Send Time Optimization?

Send Time Optimization staggers an email campaign launch over 24 hours and sends each email at the time when the recipient is most likely to open it.

aim-sto-workflow

How does it work?

It uses machine learning to analyze your contacts’ behavior and identify the times when they are most responsive. This is independent of timezone, language or region.

Furthermore, the algorithm analyzes new responses for every contact on a daily basis and updates its model accordingly. This means that the results get better and better over time.

For new contacts with no behavior history, their first email campaigns will be sent at a default time calculated by us.

How do I activate it?

If Send Time Optimization is enabled for your account, it will appear on the Scheduling page of all campaigns where it is available. You can turn it on and off via the switch.

sto-enable

Once enabled, it will start to calculate the sending times for each recipient when the campaign is launched. If the campaign is scheduled, the calculation will begin at the time of scheduled launch.

How does this affect the campaign launch?

The campaign is split up into 12 child campaigns, sent on the hour at two-hour intervals. These intervals are based on the even hours according to Central European time (CET). Each recipient in the launch list is assigned to the campaign closest to their optimal response time.

As the child campaigns for each contact are calculated new for each campaign, the actual launch will be delayed by some minutes. This delay depends on the size of your database and the launch list, but from our tests we would expect not more than a minute per 100,000 contacts as the upper limit. You can track the calculations with the progress bar:

aim-sto-calculating

Important: The first child campaign will be sent at the next available time slot after calculation has finished. You may therefore want to schedule a launch according to your UTC offset, and allow 15 minutes extra for the calculation.

What effect does this have on reporting?

The campaign will immediately appear as Launched in the Emails list but will not appear in the Email Analysis list until the launch has actually begun. Each campaign sent using this feature is flagged by an icon.

aim-sto-results-list-icon

The campaign summary can be seen aggregated, or individually for each child campaign by clicking the plus sign.

aim-sto-reporting-expanded

Are there any other considerations?

Send Time Optimization can currently only be enabled for ad hoc, batch email campaigns. It cannot be used if the Advanced Scheduling is turned on.

Additionally, Send Time Optimization is independent of the Frequency Cap. If the Frequency Cap is active, this will apply to each child campaign at the moment of launch.

When using Send Time optimization for the very first time, the first campaign to be sent using it will be delayed by up to one hour as the initial model is built up from past behavior data. After this, you can use it for every campaign with only a minimal delay while the model is updated.

Why is this good for my customers and for me?

You want your emails to sit as close to the top of the inbox as possible when the customer opens it. Send Time Optimization is designed to do just that. For your customers, this is one more example of how you are treating them as an individual, strengthening their loyalty to your brand and improving their experience.

Best practices

Since the launch is spread over 24 hours, the actual launch time is no longer so important. So for regular newsletters you can schedule them half an hour in advance to compensate for the calculation time.

However, for time-sensitive emails such as limited special offers or discounts, you should consider the duration of the offer before using this feature. If an offer is only available for a 24-hour period, for example, you will not be giving all your customers the same advantage if Send time optimization is used.