How good are these forecasts?
Every forecast scored on seasons the model never saw while its settings were chosen.
Held-back seasons
| Forecast | Forecasts | Log loss | Favourite won |
|---|---|---|---|
| The model | 2629 | 0.455 | 77% |
| Base rate | 2629 | 0.691 | 56% |
| Recent form | 2629 | 0.586 | 70% |
ESPN's women's lacrosse coverage grows sharply from 2019, so the ratings have fewer seasons to learn from than the men's page; the first season only warms them up.
The title odds use an approximate 32-team tournament of the best teams by simulated wins and rating, on neutral fields. The real field is 29, with automatic bids for conference champions; the model doesn't know conference membership, so it picks on merit.
Draw controls and goalies matter a lot; the model only sees team results.
The season runs from February to Memorial Day; outside it the pages show how the last one finished.
Questions and answers
How accurate are PodiumOracle's NCAA women's lacrosse predictions?
On 2,629 games from held-back seasons (2024 to 2026), which the model never saw while it was tuned, the side it favoured won 77% of the time. Its log loss was 0.455, against 0.691 for the base rate and 0.586 for recent form.