SFM Tracker

Weekly Top 20 Predictions by League

Matchday 10: Premier League (Completed Games Only)
One round — 17 graded picks. Small samples swing hard. See the full season.
SFM Top 20 Predictions
17
Predictions
6
Scored
35.3%
Hit Rate
Naive Top 20 Predictions
13
Predictions
2
Scored
15.4%
Hit Rate
SFM outperforms Naive:
35.3% vs 15.4% (+19.9 pp)
Brier Score: Premier League
0.2186
SFM
0.1727
Naive
Naive 0.1727 < SFM 0.2186
Calibration: Premier League
Hit Rate Over Time: Premier League (SFM vs Naive)
Premier League 2026/27 GD10 Completed
This GD: 35.3% (6/17) Overall: 35.3% (6/17) 1 gamedays completed
Rank Player Team vs SFM Naive Result
1 Erling Haaland Manchester City Nottingham Forest 60.1% 58.1% No goal
2 Alexander Isak Liverpool Crystal Palace 53.7% 34.9% 1 goal
3 Kai Havertz Arsenal Hull City 43.7% 24.5% No goal
4 Thierno Barry Everton Coventry City 42.9% 22.9% 2 goals
5 Nicolas Jackson Aston Villa Manchester United 41.5% 30.1% 1 goal
6 Bryan Mbeumo Manchester United Aston Villa 38.6% 26.4% No goal
7 Joao Pedro Chelsea Sunderland 36.3% 25.8% Did not play
8 Bukayo Saka Arsenal Hull City 35.2% 23.7% Did not play
9 Brian Brobbey Sunderland Chelsea 33.9% 20.2% No goal
10 Evanilson AFC Bournemouth Ipswich Town 33.7% 21.2% 1 goal
11 Dominic Calvert Lewin Leeds United Tottenham Hotspur 31.4% 23.1% No goal
12 Benjamin Sesko Manchester United Aston Villa 30.8% 33.2% Did not play
13 Marcus Tavernier AFC Bournemouth Ipswich Town 30.1% 14.4% No goal
14 Cole Palmer Chelsea Sunderland 28.2% 33.6% No goal
15 Morgan Rogers Chelsea Sunderland 27.7% 21.9% No goal
16 Bruno Fernandes Manchester United Aston Villa 27.5% 22.3% 1 goal
17 Kiernan Dewsbury Hall Everton Coventry City 27.2% 22.8% 1 goal
18 Zian Flemming Ipswich Town AFC Bournemouth 25.1% 31.6% No goal
19 Matheus Cunha Manchester United Aston Villa 24.1% 22.7% No goal
20 Rayan AFC Bournemouth Ipswich Town 24.0% 28.3% 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.