SFM Tracker

Weekly Top 20 Predictions by League

Matchday 9: Premier League (Completed Games Only)
One round — 15 graded picks. Small samples swing hard. See the full season.
SFM Top 20 Predictions
15
Predictions
6
Scored
40.0%
Hit Rate
Naive Top 20 Predictions
15
Predictions
3
Scored
20.0%
Hit Rate
SFM outperforms Naive:
40.0% vs 20.0% (+20.0 pp)
Brier Score: Premier League
0.2818
SFM
0.1677
Naive
Naive 0.1677 < SFM 0.2818
Calibration: Premier League
Hit Rate Over Time: Premier League (SFM vs Naive)
Premier League 2026/27 GD09 Completed
This GD: 40.0% (6/15) Overall: 40.0% (6/15) 1 gamedays completed
Rank Player Team vs SFM Naive Result
1 Erling Haaland Manchester City Brighton & Hove Albion 67.2% 58.1% No goal
2 Alexander Isak Liverpool Arsenal 52.3% 34.9% No goal
3 Nicolas Jackson Aston Villa Fulham 46.3% 30.1% 1 goal
4 Joao Pedro Chelsea Manchester United 41.3% 25.8% Did not play
5 Brian Brobbey Sunderland Coventry City 36.0% 20.2% No goal
6 Bryan Mbeumo Manchester United Chelsea 35.9% 26.4% No goal
7 Marcus Tavernier AFC Bournemouth Leeds United 31.8% 14.4% No goal
8 Evanilson AFC Bournemouth Leeds United 30.0% 21.2% 1 goal
9 Thierno Barry Everton Newcastle United 28.9% 22.9% 1 goal
10 Omar Marmoush Tottenham Hotspur Crystal Palace 28.1% 26.7% No goal
11 Morgan Rogers Chelsea Manchester United 27.8% 21.9% 1 goal
12 Kevin Schade Brentford Nottingham Forest 27.6% 18.0% No goal
13 Kai Havertz Arsenal Liverpool 27.5% 24.5% 1 goal
14 Cole Palmer Chelsea Manchester United 27.3% 33.6% 1 goal
15 Benjamin Sesko Manchester United Chelsea 27.2% 33.2% Did not play
16 Ollie Watkins Aston Villa Fulham 26.8% 33.8% Did not play
17 Dominic Calvert Lewin Leeds United AFC Bournemouth 25.7% 23.1% No goal
18 Dominic Solanke Tottenham Hotspur Crystal Palace 25.1% 20.8% No goal
20 Bukayo Saka Arsenal Liverpool 24.8% 23.7% Did not play
20 James Maddison Tottenham Hotspur Crystal Palace 24.3% 22.0% Did not play
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.