Technical

How LTV.ai shapes exactly who receives a campaign

LTV.ai shapes audiences with boolean logic over predictive segments, smart follow-up exclusions with value floors, and holdouts for clean lift measurement.

Soft watercolor of a sunlit clearing within a wider shaded meadow, light falling on one patch.

Quick answer: LTV.ai lets you add high-potential cohorts and remove customers who will not engage, using boolean logic over predictive segments. It suggests follow-up exclusions of unlikely-to-click recipients with value floors so high-value customers are never dropped, and it supports holdouts for clean lift measurement.

One audience abstraction

Every mechanism produces or trims a single audience object that the send pipeline consumes. That keeps audience shaping consistent whether it comes from a smart list, a follow-up exclusion, a suppression rule, or a manual upload.

Smart lists from predictions

Inclusion and exclusion lists are built as boolean formulas over predictive segments: for example, exclude high-churn or low-click customers, or include high purchase-intent and discount-insensitive customers. These are suggested per campaign and toggled on or off.

Follow-up exclusions, done carefully

When a campaign is a follow-up to a recent send, the system suggests excluding recipients unlikely to click. This is bounded: a cap on how much of the audience can be trimmed and value floors so high-value customers are never silently removed. A preview shows the impact before anything is committed, and the trimmed audience is materialized with a distinct name for an auditable trail.

Holdouts for honest measurement

The audience system supports holdouts, a carved-out control group that receives nothing, so lift can be measured cleanly against customers who did not get the campaign. This is what turns a revenue number into an incrementality number.

Frequently asked questions

Could a follow-up exclusion drop my best customers? No. Value floors protect high-value customers from being excluded.

What is a holdout for? Measuring true incremental lift against a control that received nothing.


Part of the machine learning behind LTV.ai, a series on how the platform works under the hood.

See it on your store: book a demo.