#Data Cloud · Trailblazer Community

MI

Identity resolution rulesets — when to use deterministic vs. probabilistic?

We have ~40M unified profiles and the dedupe rate is lower than I expected. Walking through whether probabilistic blending makes sense for the consumer side of the org.

Accepted answer

JY

Jasmine Young

Senior Salesforce Administrator · 3 hrs ago

We ran the same comparison last quarter. Probabilistic was the right call for us but we capped the confidence threshold high — 0.95+ only. Caught the household collapse problem you're worried about by adding a 'shared-address-but-different-DOB' exclusion to the ruleset.

MI

Data Cloud Activation — best practices for high-frequency segment refresh?

Activating a churn-risk segment every 15 minutes. Activation runtime is creeping. Curious if anyone has tuning patterns beyond the docs.

SV

Data Cloud identity resolution — shadow mode results, week 2

Two weeks into shadow mode for probabilistic blending. Sharing what we've learned: 87% match agreement with our deterministic baseline, a few interesting edge cases.