SFM Tracker

Weekly Top 20 Predictions by League

Overall Performance: Premier League (Completed Games Only)
SFM Top 20 Predictions
520
Predictions
104
Scored
20.0%
Hit Rate
Naive Top 20 Predictions
520
Predictions
99
Scored
19.0%
Hit Rate
SFM outperforms Naive:
20.0% vs 19.0% (+1.0 pp)
Brier Score: Premier League
0.1574
SFM
0.1564
Naive
Naive 0.1564 < SFM 0.1574
Calibration: Premier League
Hit Rate Over Time: Premier League (SFM vs Naive)
Premier League 2025/26 GD27 Upcoming
Overall: 20.0% (104/520) 26 gamedays completed
History: GD1 GD2 GD3 GD4 GD5 GD6 GD7 GD8 GD9 GD10 GD11 GD12 GD13 GD14 GD15 GD16 GD17 GD18 GD19 GD20 GD21 GD22 GD23 GD24 GD25 GD26 GD27
Rank Player Team vs SFM Naive Result
1 Erling Haaland Manchester City Newcastle United 54.7% 60.9% Pending
2 Ollie Watkins Aston Villa Leeds United 38.4% 34.8% Pending
3 Mohamed Salah FC Liverpool Nottingham Forest 32.4% 42.6% Pending
4 Cole Palmer FC Chelsea FC Burnley 31.9% 33.8% Pending
5 Joergen Strand Larsen Crystal Palace Wolverhampton Wanderers 28.6% 22.7% Pending
6 Alexander Isak FC Liverpool Nottingham Forest 27.4% 33.1% Pending
7 Jean Philippe Mateta Crystal Palace Wolverhampton Wanderers 26.9% 26.4% Pending
8 Callum Wilson West Ham United AFC Bournemouth 25.8% 31.5% Pending
9 Jadon Sancho Aston Villa Leeds United 25.2% 25.8% Pending
10 Benjamin Sesko Manchester United FC Everton 24.7% 33.9% Pending
11 Phil Foden Manchester City Newcastle United 24.7% 27.7% Pending
12 Tammy Abraham Aston Villa Leeds United 24.6% 25.7% Pending
13 Taiwo Awoniyi Nottingham Forest FC Liverpool 23.4% 27.1% Pending
14 Randal Kolo Muani Tottenham Hotspur FC Arsenal 23.0% 28.0% Pending
15 Omar Marmoush Manchester City Newcastle United 22.5% 20.5% Pending
16 Bukayo Saka FC Arsenal Tottenham Hotspur 22.0% 23.6% Pending
17 Morgan Rogers Aston Villa Leeds United 22.0% 23.9% Pending
18 Kai Havertz FC Arsenal Tottenham Hotspur 22.0% 24.7% Pending
19 Gabriel Jesus FC Arsenal Tottenham Hotspur 21.9% 28.7% Pending
20 Chris Wood Nottingham Forest FC Liverpool 21.9% 27.5% Pending
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.