SFM Tracker

Weekly Top 20 Predictions by League

Reset
Overall Performance: Premier League (Completed Games Only)
SFM Top 20 Predictions
760
Predictions
159
Scored
20.9%
Hit Rate
Naive Top 20 Predictions
760
Predictions
152
Scored
20.0%
Hit Rate
SFM outperforms Naive:
20.9% vs 20.0% (+0.9 pp)
Brier Score: Premier League
0.1624
SFM
0.1609
Naive
Naive 0.1609 < SFM 0.1624
Calibration: Premier League
Hit Rate Over Time: Premier League (SFM vs Naive)
Premier League 2025/26 GD36 Completed
This GD: 25.0% (5/20) Overall: 20.9% (159/760) 38 gamedays completed
History: GD01 GD02 GD03 GD04 GD05 GD06 GD07 GD08 GD09 GD10 GD11 GD12 GD13 GD14 GD15 GD16 GD17 GD18 GD19 GD20 GD21 GD22 GD23 GD24 GD25 GD26 GD27 GD28 GD29 GD30 GD31 GD32 GD33 GD34 GD35 GD36 GD37 GD38
Rank Player Team vs SFM Naive Result
1 Erling Haaland Manchester City FC Brentford 58.3% 60.9% 1 goal
2 Ollie Watkins Aston Villa FC Burnley 38.1% 34.8% 1 goal
3 Alexander Isak FC Liverpool FC Chelsea 35.3% 33.1% No goal
4 Randal Kolo Muani Tottenham Hotspur Leeds United 29.8% 28.0% No goal
5 Phil Foden Manchester City FC Brentford 29.1% 27.7% No goal
6 Taiwo Awoniyi Nottingham Forest Newcastle United 27.5% 27.1% No goal
7 Omar Marmoush Manchester City FC Brentford 26.6% 20.5% 1 goal
8 Kai Havertz FC Arsenal West Ham United 26.4% 24.7% No goal
9 Bukayo Saka FC Arsenal West Ham United 26.4% 23.6% No goal
10 Cody Gakpo FC Liverpool FC Chelsea 26.3% 25.9% No goal
11 Chris Wood Nottingham Forest Newcastle United 25.9% 27.5% No goal
12 Jack Hinshelwood Brighton & Hove Albion Wolverhampton Wanderers 25.9% 20.6% 1 goal
13 Eberechi Eze FC Arsenal West Ham United 25.5% 23.3% No goal
14 Savio Manchester City FC Brentford 25.3% 21.0% No goal
15 Rodrigo Muniz FC Fulham AFC Bournemouth 24.5% 30.2% No goal
16 Antoine Semenyo Manchester City FC Brentford 24.4% 14.6% No goal
17 Kaoru Mitoma Brighton & Hove Albion Wolverhampton Wanderers 24.0% 18.9% No goal
18 Richarlison Tottenham Hotspur Leeds United 23.4% 21.9% No goal
19 Yasin Ayari Brighton & Hove Albion Wolverhampton Wanderers 23.1% -- No goal
20 Leandro Trossard FC Arsenal West Ham United 23.0% 20.3% 1 goal
Understanding Hit Rate vs Brier Score

You might notice that hit rate and Brier Score can tell different stories.

Hit Rate

Simply counts: "How many of my top 20 picks scored?"

A naive model that always picks proven strikers (Haaland, Kane) will have a high hit rate because these players score often, regardless of the match context.

Brier Score

Asks: "How accurate were the probability estimates?"

If SFM says "32% chance" and Naive says "38% chance" for the same player who doesn't score, SFM gets a better Brier Score because its estimate was closer to reality.

Bottom line: Hit rate measures selection quality (who you pick), while Brier Score measures probability quality (how well-calibrated your predictions are). A model can pick slightly fewer scorers but still be more valuable if its probabilities are more trustworthy for betting or decision-making.
SFM Tracker
Top 20 Selection

For each league and gameday, we select the 20 players with the highest median probability of scoring at least one goal as predicted by the SFM.

Frozen Predictions

Predictions are locked before matches are played. This ensures transparent, verifiable performance tracking.

Fair Comparison

We compare SFM's top 20 picks against Naive's own top 20 picks (ranked by historical average). This is apples-to-apples.

Brier Score

Evaluation metric for probabilistic predictions. Measures both calibration and discrimination. Lower is better.