Computed trait
What is Computed trait?
A computed trait is a customer attribute a data platform derives automatically from raw event and profile data — such as lifetime spend, days since last purchase, or predicted churn risk — rather than a value that was directly recorded somewhere. Computed traits refresh on a schedule or in real time as new events arrive, and are what let a marketing or messaging campaign target 'customers likely to churn in 30 days' instead of only filtering on raw, unprocessed fields.
More detail
Computed traits range from simple aggregates (total orders, average order value) to model-driven scores (churn risk, predicted lifetime value) that require a trained model running behind the scenes.
Because a computed trait recalculates as new data arrives, it stays current without anyone manually updating a spreadsheet or static list, which is what makes it useful for ongoing, automated targeting.
Frequently asked
- How is a computed trait different from a raw data field?
- A raw field is a value directly recorded from a source system, like a signup date; a computed trait is derived by processing raw data — aggregating, scoring, or calculating — to produce something more useful for targeting, like churn risk or lifetime spend.
- Do computed traits update automatically?
- Yes, typically on a schedule or in near real time as new underlying events arrive, so a segment built on a computed trait like 'high churn risk' stays current without any manual recalculation.
See also
Build it on Orbit
Voice, messaging, email, video, and AI agents on one platform and one pay-as-you-go bill. Start free — no credit card required.