SFM Tracker

Weekly Top 20 Predictions by League

Reset
Matchday 4: Premier League (Completed Games Only)
One round — 17 graded picks. Small samples swing hard. See the full season.
SFM Top 20 Predictions
17
Predictions
7
Scored
41.2%
Hit Rate
Naive Top 20 Predictions
13
Predictions
3
Scored
23.1%
Hit Rate
SFM outperforms Naive:
41.2% vs 23.1% (+18.1 pp)
Brier Score: Premier League
0.2639
SFM
0.1675
Naive
Naive 0.1675 < SFM 0.2639
Calibration: Premier League
Hit Rate Over Time: Premier League (SFM vs Naive)
Premier League 2026/27 GD04 Completed
This GD: 41.2% (7/17) Overall: 41.2% (7/17) 1 gamedays completed
History: GD01 GD02 GD03 GD04 GD05
Rank Player Team vs SFM Naive Result
1 Alexander Isak Liverpool Fulham 59.2% 34.4% No goal
2 Erling Haaland Manchester City Manchester United 50.3% 58.3% 1 goal
3 Kai Havertz Arsenal Sunderland 40.7% 24.1% No goal
4 Joao Pedro 10 Chelsea Hull City 36.6% 26.2% 1 goal
5 Cole Palmer Chelsea Hull City 36.3% 33.1% No goal
6 Bruno Fernandes Manchester United Manchester City 33.2% 22.0% No goal
7 Bukayo Saka Arsenal Sunderland 32.6% 22.4% 1 goal
8 Cody Gakpo Liverpool Fulham 31.6% 22.9% No goal
9 Bryan Mbeumo Manchester United Manchester City 31.3% 26.8% No goal
11 Marcus Tavernier AFC Bournemouth Brentford 28.1% 14.6% 1 goal
13 Victor Mu Oz Liverpool Fulham 27.9% 16.2% No goal
14 Ollie Watkins Aston Villa Nottingham Forest 27.8% 33.9% Did not play
15 Dominic Calvert Lewin Leeds United Newcastle United 27.4% 23.3% 1 goal
16 Jack Hinshelwood Brighton & Hove Albion Coventry City 26.6% 19.1% Did not play
17 Jean Philippe Mateta Crystal Palace Ipswich Town 26.1% 27.9% Did not play
18 Hugo Ekitike Liverpool Fulham 25.8% 28.7% Did not play
19 Nicolas Jackson Aston Villa Nottingham Forest 25.7% 29.5% No goal
20 Joergen Strand Larsen Crystal Palace Ipswich Town 25.7% 22.3% 1 goal
19 Anan Khalaili Crystal Palace Ipswich Town 23.8% -- 1 goal
18 Yoane Wissa Newcastle United Leeds United 23.5% 25.1% No goal
16 Thierno Barry Everton Tottenham Hotspur 22.8% 23.5% 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.