SFM Tracker

Weekly Top 20 Predictions by League

Matchday 6: 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
3
Scored
23.1%
Hit Rate
SFM outperforms Naive:
35.3% vs 23.1% (+12.2 pp)
Brier Score: Premier League
0.2112
SFM
0.1679
Naive
Naive 0.1679 < SFM 0.2112
Calibration: Premier League
Hit Rate Over Time: Premier League (SFM vs Naive)
Premier League 2026/27 GD06 Completed
This GD: 35.3% (6/17) Overall: 35.3% (6/17) 1 gamedays completed
Rank Player Team vs SFM Naive Result
1 Alexander Isak Liverpool Manchester City 53.8% 34.9% Did not play
2 Erling Haaland Manchester City Liverpool 51.6% 58.1% 1 goal
3 Kai Havertz Arsenal Leeds United 40.2% 24.5% No goal
4 Bukayo Saka Arsenal Leeds United 39.2% 23.7% No goal
5 Joao Pedro Chelsea AFC Bournemouth 38.8% 25.8% 2 goals
6 Brian Brobbey Sunderland Brighton & Hove Albion 37.9% 20.2% Did not play
7 Bruno Fernandes Manchester United Tottenham Hotspur 36.3% 22.3% No goal
8 Bryan Mbeumo Manchester United Tottenham Hotspur 35.9% 26.4% 1 goal
9 Benjamin Sesko Manchester United Tottenham Hotspur 35.4% 33.2% Did not play
10 Cole Palmer Chelsea AFC Bournemouth 31.8% 33.6% No goal
11 Nicolas Jackson Aston Villa Brentford 31.4% 30.1% 1 goal
12 Morgan Rogers Chelsea AFC Bournemouth 29.9% 21.9% 1 goal
13 Marcus Tavernier AFC Bournemouth Chelsea 29.2% 14.4% No goal
14 Emersonn Ipswich Town Fulham 29.0% 19.9% No goal
15 Matheus Cunha Manchester United Tottenham Hotspur 28.2% 22.7% No goal
16 Kevin Schade Brentford Aston Villa 27.0% 18.0% No goal
17 Thierno Barry Everton Hull City 26.8% 22.9% 1 goal
18 Zian Flemming Ipswich Town Fulham 26.2% 31.6% No goal
19 Yoane Wissa Newcastle United Coventry City 25.9% 24.5% No goal
20 Joergen Strand Larsen Crystal Palace Nottingham Forest 25.9% 22.1% 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.