Learning loop

The scoring engine retrains nightly on the last 90 days of outcomes. Every weight change is versioned, reviewable, and rollbackable.

Back to board
Current version
v14
Versions shipped
5
Retention
Every version, forever

Version history

VersionTrainedSkillDistancePriorityPerformanceAvailability
v145/3/202635+125-1201010
v135/1/202634+126-1201010
v124/27/202633+127-1201010
v114/20/202632+228-2201010
v104/13/20263030201010

Why this matters to an acquirer

  1. Every historical assignment pins a weights_version, so any decision can be re-run against the exact inputs that produced it.
  2. From v10 to v14 the model has shifted 5 points toward skill match, reflecting outcome data that proved the right skill matters more than the shortest drive.
  3. Rolling back is a single API call. No model retraining, no downtime, no black box.