Explain what happened
Why any recommendation happened
Trace a result back to what produced it, and read relevance, engagement, coverage, diversity, novelty, catalogue exposure, latency and cost across every model and every surface.
What it does
The mechanism
- 01
Any recommendation can be traced back to the interests, interactions, content similarities and business rules that produced it.
- 02
Exposure is measured as well as engagement: you can see how attention is distributed across genres, creators, products, providers and editorial categories.
What it gets you
Three things you can point at
01
Why this was recommended
A decomposition of a single result, with the rule that fired named alongside the interests, interactions and similarities that moved it.
02
Replay the past
Run a prospective model against historical user journeys to see how its recommendations would have differed.
03
Know when it is uncertain
Confidence, data sparsity and disagreement between the candidate models are reported rather than hidden behind a uniformly confident answer.