SFM Tracker

Weekly Top 20 Predictions by League

Reset
Overall Performance: Premier League (Completed Games Only)
SFM Top 20 Predictions
620
Predictions
122
Scored
19.7%
Hit Rate
Naive Top 20 Predictions
620
Predictions
118
Scored
19.0%
Hit Rate
SFM outperforms Naive:
19.7% vs 19.0% (+0.6 pp)
Brier Score: Premier League
0.1577
SFM
0.1587
Naive
SFM 0.1577 < Naive 0.1587
Calibration: Premier League
Hit Rate Over Time: Premier League (SFM vs Naive)
Premier League 2025/26 GD30 Completed
This GD: 5.0% (1/20) Overall: 19.7% (122/620) 31 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
Rank Player Team vs SFM Naive Result
1 Erling Haaland Manchester City West Ham United 51.6% 60.9% No goal
2 Mohamed Salah FC Liverpool Tottenham Hotspur 41.1% 42.6% No goal
3 Benjamin Sesko Manchester United Aston Villa 30.1% 33.9% 1 goal
4 Cole Palmer FC Chelsea Newcastle United 29.3% 33.8% No goal
5 Ollie Watkins Aston Villa Manchester United 28.4% 34.8% No goal
6 Kai Havertz FC Arsenal FC Everton 27.5% 24.7% No goal
7 Bukayo Saka FC Arsenal FC Everton 27.4% 23.6% No goal
8 Hugo Ekitike FC Liverpool Tottenham Hotspur 27.2% 24.7% No goal
9 Eberechi Eze FC Arsenal FC Everton 26.6% 23.3% No goal
10 Joergen Strand Larsen Crystal Palace Leeds United 26.6% 22.7% No goal
11 Cody Gakpo FC Liverpool Tottenham Hotspur 26.5% 25.9% No goal
12 Jean Philippe Mateta Crystal Palace Leeds United 24.9% 26.4% No goal
13 Taiwo Awoniyi Nottingham Forest FC Fulham 24.6% 27.1% No goal
14 Gabriel Martinelli FC Arsenal FC Everton 24.1% 20.5% No goal
15 Phil Foden Manchester City West Ham United 22.4% 27.7% No goal
16 Florian Wirtz FC Liverpool Tottenham Hotspur 22.0% 20.4% No goal
17 Nonso Madueke FC Arsenal FC Everton 21.5% 12.5% No goal
18 Mikkel Damsgaard FC Brentford Wolverhampton Wanderers 21.2% -- No goal
19 Keane Lewis Potter FC Brentford Wolverhampton Wanderers 21.1% -- No goal
20 Yegor Yarmolyuk FC Brentford Wolverhampton Wanderers 20.8% -- No 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.