Cleaning the Glass splits plays into half-court, transition and putback contexts. Those same easy-to-understand numbers haven't been publicly available in the same way for the WNBA.
So, let's fix that.
Introducing Cleaning the Glass-style contextual stats for the WNBA!
I watched 14 WNBA games from 2026 and hand-labeled 2,538 plays as half-court, transition, scramble (putbacks and quick kickouts) or other.
Then I built a classifier to estimate those same contexts from play-by-play data alone.
Here are the definitions I used to label plays:
Then I built a classifier to estimate those same contexts from play-by-play data alone.
Here are the definitions I used to label plays:
The 2,538 plays, with their manual labels, were split into two sets:
Five games (892 plays) were used to train and tune a rules-based classifier, along with other machine learning models.
Nine games (1,646 plays) were used to test how the models performed on unseen data.
Five games (892 plays) were used to train and tune a rules-based classifier, along with other machine learning models.
Nine games (1,646 plays) were used to test how the models performed on unseen data.
Every effort was made to make the labels accurate and precise.
The rules-based classifier, which bundles together 20 if-then style rules, achieved 94.8% overall accuracy, 93.0% overall precision and a 92.2% F1 score, outperforming other ML models like HGBC, SVM, XGBoost and KNN.
The rules-based classifier, which bundles together 20 if-then style rules, achieved 94.8% overall accuracy, 93.0% overall precision and a 92.2% F1 score, outperforming other ML models like HGBC, SVM, XGBoost and KNN.
About nine plays per game (5% of plays) might be misclassified. In general, the rules-based classifier modestly undercounts transition plays
Differentiating between some half-court and transition plays (like seven-seconds-or-less style plays) can be tough, even for the human eye
Differentiating between some half-court and transition plays (like seven-seconds-or-less style plays) can be tough, even for the human eye
Point being: It’s best to read the labels as estimates, useful ones at that.
Enough about the methodology, though! With the predicted labels in hand, it’s easy to calculate context-based stats.
Here’s the defensive variant of the first table in the original tweet:
Enough about the methodology, though! With the predicted labels in hand, it’s easy to calculate context-based stats.
Here’s the defensive variant of the first table in the original tweet:
Credit is due to @cleantheglass (obviously!), whose definitions I used, and also @BillyFryer42, who gave advice on how to think about plays that blurred the line b/w half court and transition.
I broke down the top teams in each context for @SInow here: si.com/wnba/breaking-…
I broke down the top teams in each context for @SInow here: si.com/wnba/breaking-…
Generated by Thread Navigator
Press ⌘ + S to quick-export