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 | 450 | 0.972 | 55% |
| Base rate | 450 | 1.027 | 49% |
| Recent form | 450 | 1.011 | 49% |
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 |
|---|---|---|---|---|---|
| Bookmakers (Pinnacle, DraftKings, bet365) | 22 Jan 2026 | 115 | 0.882 | 0.889 | 0.8% |
| Polymarket | 13 Feb 2025 | 250 | 0.946 | 0.939 | −0.7% |
| Kalshi | 8 May 2025 | 193 | 0.903 | 0.898 | −0.5% |
Clubs are rated on their domestic league games as well as all three UEFA competitions, so a Norwegian champion and a mid-table Premier League side sit on one scale, linked by European meetings. Only Europa League matches are scored in the track record.
Knockout ties are two legs; the simulation plays each as one game on neutral ground.
Clubs from leagues football-data.co.uk doesn't carry (Czechia, Croatia, Serbia, Ukraine, Israel, Cyprus and others) are rated only on their European matches.
Countries are linked only through the UEFA competitions, and ESPN's feeds leave out the qualifying rounds.
Questions and answers
How accurate are PodiumOracle's Europa League predictions?
On 450 games from held-back seasons (2024–25 to 2026–27), which the model never saw while it was tuned, the side it favoured won 55% of the time. Its log loss was 0.972, against 1.027 for the base rate and 1.011 for recent form. Against the betting markets on the same finished games, its log loss was 0.882 against the bookmakers' 0.889 over 115 games, 0.946 against Polymarket's 0.939 over 250 games and 0.903 against Kalshi's 0.898 over 193 games (lower is better).