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 | 702 | 0.981 | 54% |
| Base rate | 702 | 1.058 | 46% |
| Recent form | 702 | 1.016 | 53% |
| Betting market | 702 | 0.964 | 55% |
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) | 23 Jan 2026 | 232 | 0.997 | 0.982 | −1.5% |
| Polymarket | 15 Aug 2025 | 350 | 0.989 | 0.967 | −2.2% |
| Kalshi | 15 Aug 2025 | 389 | 0.986 | 0.965 | −2.1% |
A draw is its own outcome: the model has a band around an even contest in which a draw is the likeliest single result, fit on the tuning seasons.
The market comparison uses the bookmakers' closing odds with their margin taken out.
Team news, injuries and rotation for European games are not in the model.
Expected goals are not in the rating yet; it learns only from results.
Questions and answers
How accurate are PodiumOracle's Ligue 1 predictions?
On 702 games from held-back seasons (2024–25 to 2026–27), which the model never saw while it was tuned, the side it favoured won 54% of the time. Its log loss was 0.981, against 1.058 for the base rate and 1.016 for recent form, and 0.964 for the closing betting odds. Against the betting markets on the same finished games, its log loss was 0.997 against the bookmakers' 0.982 over 232 games, 0.989 against Polymarket's 0.967 over 350 games and 0.986 against Kalshi's 0.965 over 389 games (lower is better).