SFM Tracker

Weekly Top 20 Predictions by League

Reset
Matchday 2: Premier League (Completed Games Only)
One round — 20 graded picks. Small samples swing hard. See the full season.
SFM Top 20 Predictions
20
Predictions
7
Scored
35.0%
Hit Rate
Naive Top 20 Predictions
10
Predictions
5
Scored
50.0%
Hit Rate
Naive outperforms SFM:
50.0% vs 35.0%
Brier Score: Premier League
0.2365
SFM
0.2669
Naive
SFM 0.2365 < Naive 0.2669
Calibration: Premier League
Hit Rate Over Time: Premier League (SFM vs Naive)
Premier League 2026/27 GD02 Completed
This GD: 35.0% (7/20) Overall: 35.0% (7/20) 1 gamedays completed
History: GD01 GD02 GD03 GD04 GD05
Rank Player Team vs SFM Naive Result
1 Kai Havertz Arsenal Aston Villa 44.1% 24.1% No goal
2 Jack Hinshelwood Brighton & Hove Albion Chelsea 42.9% 19.1% Did not play
3 Cody Gakpo Liverpool Nottingham Forest 41.5% 22.9% No goal
4 Joao Pedro 10 Chelsea Brighton & Hove Albion 36.5% 26.2% 2 goals
5 Cole Palmer Chelsea Brighton & Hove Albion 36.3% 33.1% 1 goal
6 Nilson Angulo Sunderland Fulham 36.1% -- No goal
7 Bukayo Saka Arsenal Aston Villa 35.6% 22.4% 1 goal
8 Marcus Tavernier AFC Bournemouth Everton 35.4% 14.6% No goal
9 Benjamin Sesko Manchester United Ipswich Town 33.9% 33.2% No goal
10 Dominik Szoboszlai Liverpool Nottingham Forest 31.0% 15.1% No goal
11 Anton Stach Leeds United Brentford 30.7% -- No goal
12 Thierno Barry Everton AFC Bournemouth 30.6% 23.5% No goal
13 Gonzalo Garcia Fulham Sunderland 30.0% 12.9% No goal
14 Alexander Isak Liverpool Nottingham Forest 29.3% 34.4% 1 goal
15 Morgan Rogers Chelsea Brighton & Hove Albion 27.9% 21.9% No goal
16 Bryan Mbeumo Manchester United Ipswich Town 27.8% 26.8% 1 goal
17 Emersonn Ipswich Town Manchester United 27.5% 19.9% No goal
18 Erling Haaland Manchester City Crystal Palace 27.3% 58.3% 2 goals
19 Martin Oedegaard Arsenal Aston Villa 27.2% 16.6% No goal
20 Matheus Cunha Manchester United Ipswich Town 26.8% 23.1% No goal
19 Anthony Elanga Newcastle United Tottenham Hotspur 26.0% 8.8% 1 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.