At a glance: Learn how to set up your ad engagement data so AppsFlyer can apply probabilistic modelling when deterministic signals aren’t available.
About probabilistic modeling
AppsFlyer uses probabilistic modeling as a privacy-preserving statistical method to report on how app developers’ marketing campaigns are performing. It produces aggregate campaign-level performance reports for app developers.
Implementation characteristics
- Uses statistics and is not based on unique IDs.
- It is a fallback method used when a referer or advertising IDs are unavailable. Deterministic attribution methods, i.e., clicks with referrer or ID matching, are given priority if they occur within the lookback window.
When is probabilistic modeling used?
Except where otherwise configured by the customer, probabilistic modeling will apply in cases where deterministic data is unavailable, including:
- Web-to-app conversions
- Cross-device experiences (for example, a desktop ad followed by a mobile install)
- CTV, PC, or console environments where deterministic attribution isn’t possible