This article provides tips, best practices, and common pitfalls to help you configure and optimize Optimal Send Time (OST) predictions. It covers the built-in OST options for scenarios and campaigns, as well as the OST prediction template.
Tips and best practices
1. Select a data range
The data range depends on how you use OST:
Built-in OST in scenarios or campaigns: OST uses a fixed 90-day customer event history.
OST prediction template: You can select a time frame. A longer time frame provides more behavioral data for OST to use when calculating send times. Test what works best with your dataset and campaign frequency.
2. Select events
OST optimizes for clicks by default.
The previous “optimize for open vs. click” option was removed because open event data can be unreliable.
For email, OST uses opens as a fallback only when there is insufficient click data.
Make sure your engagement tracking, especially click events, is implemented correctly. OST relies primarily on this data.
3. Set a default time as a fallback
Fallback behavior depends on where you apply OST:
Built-in OST in scenarios or campaigns: The fallback is the scheduled send time of your campaign.
OST prediction template: You define a default hour, such as 9 (9:00 UTC), for customers without enough data to calculate a personalized time.
Avoid setting the default hour to 0 (00:00 UTC) unless it aligns with your audience’s active hours.
4. Consider time zones
OST predictions and default send times are always calculated in UTC (UTC-0). The time zone in user settings does not affect calculations.
For global audiences, consider creating regional segments or using Silent hours in scenarios to avoid sending messages during night hours.
If localization is not possible, choose a balanced UTC hour, such as 14:00 UTC, to minimize sends during off-hours across key markets.
Configure messaging channels in scenarios
In scenarios, you select a messaging channel for each Wait node. Available options include:
Email
SMS, MMS, or RCS
Mobile push
Browser push
App inbox
WhatsApp
All channels
Use All channels when you want one send time across channels.
The messaging channel selector requires the Loomi AI Journey Orchestration package. Without this package, OST uses engagement data across all channels (generic OST), available with the Loomi AI Audience Optimization package.
Common pitfalls to avoid
Using sparse or incorrect event mappings: Make sure your campaign events are tracked as clicked (primary) and, for email, opened (fallback).
Expecting a minimum campaign count: OST does not require a minimum number of campaigns.
Setting a default hour outside typical engagement times: Midnight UTC is rarely optimal for global audiences.
Ignoring send strategy selection: Choosing the wrong send strategy can result in messages being sent too late or too early.
Assuming OST alone solves timing issues: OST helps with send timing, but campaign success also depends on segmentation, targeting, and relevant content.
Summary
Use these best practices to configure OST based on customers’ past engagement and choose suitable send times for your campaigns.
For more details, refer to the Optimal Send Time Prediction and Optimal Send Time in scenarios and campaigns documentation.