How good are these forecasts?
Every forecast scored on seasons the model never saw while its settings were chosen.
Against the betting markets
Each market's price before the start, scored on the same finished games as the model. A negative figure means the market was more accurate.
| Market | Since | Priced | Model log loss | Market log loss | Model vs market |
|---|---|---|---|---|---|
| Kalshi | 20 Nov 2025 | 22 | 3.355 | 3.466 | 3.2% |
This is strokes gained against the field from round scores, not shot-level Strokes Gained from ShotLink: it knows how many strokes a player took, not where they came from.
The cut is the top 65 and ties after two rounds; three-round and no-cut events are simulated as four rounds with a cut.
Withdrawals during an event count as missing the rounds they didn't play.
Course fit (a long hitter's course, a putter's course) is not in the model.
Questions and answers
How accurate are PodiumOracle's LPGA Tour predictions?
On 89 tournaments from held-back seasons (2024 to 2026), which the model never saw while it was tuned, its favourite won 20% of the time in fields of about 121, and it gave the eventual winner 4% on average. Its log loss was 3.785, against 4.741 for treating every player as equal and 4.049 for recent form. Against the betting markets on the same finished events, its log loss was 3.355 against Kalshi's 3.466 over 22 tournaments (lower is better).