Honest answer: it depends on the event class, so we report per-class F1 rather than a blended “accuracy” number. Accuracy flatters — it rewards a system for the easy negatives. F1 punishes both the missed rebound and the phantom steal, which is what a coach actually experiences.

Methodology: validated against human-tagged ground truth on 118 held-out games — roughly 9,600 events — with an event scored correct only when it lands within a two-second window of ground truth and attributes to the right player. Contact-heavy attribution (rebounds, steals) is where the remaining error lives, which is exactly what the occlusion work above would predict. A comparable engagement is documented in related case study.

The ROI math, spelled out. A platform running 10,000 games a season pays $600,000–900,000 a year for analyst tagging at $60–90 a game. The automated pipeline processes the same volume for roughly $30,000 of infrastructure. At that spread, a build of this scope recovers its cost within the first season. And at the 600,000-game design volume, the manual model is not merely expensive — it is impossible: roughly 2.1 million analyst-hours a year, or about 1,000 full-time analysts. Automation is not the cheaper option at that volume. It is the only option.