SFM Tracker

Weekly Top 20 Predictions by League

Matchday 8: Premier League (Completed Games Only)
One round — 24 graded picks. Small samples swing hard. See the full season.
SFM Top 20 Predictions
24
Predictions
4
Scored
16.7%
Hit Rate
Naive Top 20 Predictions
14
Predictions
4
Scored
28.6%
Hit Rate
Naive outperforms SFM:
28.6% vs 16.7%
Brier Score: Premier League
0.122
SFM
0.1831
Naive
SFM 0.1220 < Naive 0.1831
Calibration: Premier League
Hit Rate Over Time: Premier League (SFM vs Naive)
Premier League 2026/27 GD08 Completed
This GD: 16.7% (4/24) Overall: 16.7% (4/24) 1 gamedays completed
Rank Player Team vs SFM Naive Result
1 Erling Haaland Manchester City Aston Villa 64.4% 58.1% 1 goal
2 Alexander Isak Liverpool Brighton & Hove Albion 55.1% 34.9% 1 goal
3 Joao Pedro Chelsea Tottenham Hotspur 47.4% 25.8% Did not play
4 Bryan Mbeumo Manchester United AFC Bournemouth 43.7% 26.4% No goal
5 Kai Havertz Arsenal Everton 38.0% 24.5% No goal
6 Bukayo Saka Arsenal Everton 35.5% 23.7% Did not play
7 Brian Brobbey Sunderland Leeds United 35.3% 20.2% No goal
8 Morgan Rogers Chelsea Tottenham Hotspur 32.5% 21.9% No goal
9 Benjamin Sesko Manchester United AFC Bournemouth 32.4% 33.2% Did not play
10 Nicolas Jackson Aston Villa Manchester City 31.1% 30.1% 2 goals
11 Cole Palmer Chelsea Tottenham Hotspur 30.9% 33.6% No goal
12 Bruno Fernandes Manchester United AFC Bournemouth 30.9% 22.3% Did not play
13 Dominic Calvert Lewin Leeds United Sunderland 30.2% 23.1% No goal
14 Zian Flemming Ipswich Town Nottingham Forest 27.0% 31.6% No goal
16 Joergen Strand Larsen Crystal Palace Newcastle United 25.9% 22.1% Did not play
17 Kevin Schade Brentford Hull City 25.9% 18.0% No goal
18 Matheus Cunha Manchester United AFC Bournemouth 25.5% 22.7% No goal
19 Arnaud Kalimuendo Muinga Nottingham Forest Ipswich Town 25.1% 27.4% Did not play
20 Emanuel Emegha Chelsea Tottenham Hotspur 24.9% 33.0% Did not play
19 Dan Ndoye Nottingham Forest Ipswich Town 24.7% 10.2% No goal
4 Igor Jesus Nottingham Forest Ipswich Town 24.2% 15.0% Did not play
5 Liam Delap Nottingham Forest Ipswich Town 23.8% 17.6% No goal
17 Emersonn Ipswich Town Nottingham Forest 23.6% 19.9% No goal
20 Cody Gakpo Liverpool Brighton & Hove Albion 22.9% 22.3% No goal
6 Chris Wood Nottingham Forest Ipswich Town 22.0% 28.4% No goal
7 Morgan Gibbs White Nottingham Forest Ipswich Town 20.8% 15.9% No goal
8 Chuba Akpom Ipswich Town Nottingham Forest 18.2% 15.3% No goal
12 Callum Hudson Odoi Nottingham Forest Ipswich Town 13.6% 10.7% No goal
13 James McAtee Nottingham Forest Ipswich Town 13.1% 9.2% No goal
10 Jaden Philogene Bidace Ipswich Town Nottingham Forest 13.0% 9.1% No goal
11 Julio Enciso Ipswich Town Nottingham Forest 12.9% 10.2% 1 goal
15 Nicolas Martin Dominguez Nottingham Forest Ipswich Town 8.9% 3.6% Did not play
14 Exequiel Palacios Ipswich Town Nottingham Forest 8.2% 8.4% 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.