SFM Tracker

Weekly Top 20 Predictions by League

Reset
Matchday 5: Premier League (Completed Games Only)
One round — 17 graded picks. Small samples swing hard. See the full season.
SFM Top 20 Predictions
17
Predictions
3
Scored
17.6%
Hit Rate
Naive Top 20 Predictions
12
Predictions
4
Scored
33.3%
Hit Rate
Naive outperforms SFM:
33.3% vs 17.6%
Brier Score: Premier League
0.1266
SFM
0.1753
Naive
SFM 0.1266 < Naive 0.1753
Calibration: Premier League
Hit Rate Over Time: Premier League (SFM vs Naive)
Premier League 2026/27 GD05 Completed
This GD: 17.6% (3/17) Overall: 17.6% (3/17) 1 gamedays completed
History: GD01 GD02 GD03 GD04 GD05 GD06
Rank Player Team vs SFM Naive Result
1 Erling Haaland Manchester City Sunderland 63.5% 58.3% 1 goal
2 Alexander Isak Liverpool AFC Bournemouth 46.7% 34.4% 1 goal
4 Kai Havertz Arsenal Brighton & Hove Albion 36.9% 24.1% No goal
5 Bukayo Saka Arsenal Brighton & Hove Albion 36.5% 22.4% No goal
6 Dominic Calvert Lewin Leeds United Crystal Palace 34.4% 23.3% No goal
7 Joao Pedro 10 Chelsea Brentford 33.1% 26.2% Did not play
8 Bruno Fernandes Manchester United Fulham 32.2% 22.0% No goal
9 Thierno Barry Everton Ipswich Town 31.8% 23.5% 1 goal
8 Tyrique George Everton Ipswich Town 31.4% -- No goal
10 Marcus Tavernier AFC Bournemouth Liverpool 31.3% 14.6% No goal
11 Bryan Mbeumo Manchester United Fulham 31.2% 26.8% No goal
13 Benjamin Sesko Manchester United Fulham 30.0% 33.2% Did not play
15 Arnaud Kalimuendo Muinga Nottingham Forest Coventry City 29.8% 27.7% Did not play
16 Yoane Wissa Newcastle United Hull City 29.8% 25.1% No goal
18 Morgan Gibbs White Nottingham Forest Coventry City 26.5% 16.0% No goal
19 Kiernan Dewsbury Hall Everton Ipswich Town 26.4% 22.8% No goal
15 Cole Palmer Chelsea Brentford 26.1% 33.1% No goal
14 Keane Lewis Potter Brentford Chelsea 25.6% -- No goal
17 Dan Ndoye Nottingham Forest Coventry City 24.6% 10.4% No goal
19 Vitaly Janelt Brentford Chelsea 24.4% -- No goal
18 Ollie Watkins Aston Villa Tottenham Hotspur 23.9% 33.9% 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.