SFM Tracker

Weekly Top 20 Predictions by League

Season to date: Premier League (Completed Games Only)
Every graded pick so far. The boards below show each league's next round.
SFM Top 20 Predictions
102
Predictions
32
Scored
31.4%
Hit Rate
Naive Top 20 Predictions
75
Predictions
21
Scored
28.0%
Hit Rate
SFM outperforms Naive:
31.4% vs 28.0% (+3.4 pp)
Brier Score: Premier League
0.2043
SFM
0.186
Naive
Naive 0.1860 < SFM 0.2043
Calibration: Premier League
Hit Rate Over Time: Premier League (SFM vs Naive)
Premier League 2026/27 GD07 Upcoming
Overall: 31.4% (32/102) 6 gamedays completed
History: GD01 GD02 GD03 GD04 GD05 GD06 GD07
Rank Player Team vs SFM Naive Result
1 Erling Haaland Manchester City Ipswich Town 69.3% 58.1% Pending
2 Alexander Isak Liverpool Brentford 47.3% 34.9% Pending
3 Joao Pedro 10 Chelsea Everton 38.3% 25.8% Pending
4 Thierno Barry Everton Chelsea 37.5% 22.9% Pending
5 Nicolas Jackson Aston Villa Newcastle United 34.4% 30.1% Pending
6 Kai Havertz Arsenal Nottingham Forest 33.2% 24.5% Pending
7 Brian Brobbey Sunderland AFC Bournemouth 33.0% 20.2% Pending
8 Marcus Tavernier AFC Bournemouth Sunderland 32.8% 14.4% Pending
9 Rayan Cherki Manchester City Ipswich Town 31.8% 9.6% Pending
10 Bukayo Saka Arsenal Nottingham Forest 31.4% 23.7% Pending
11 Bryan Mbeumo Manchester United Leeds United 30.7% 26.4% Pending
13 Antoine Semenyo Manchester City Ipswich Town 29.0% 26.9% Pending
14 Kevin Schade Brentford Liverpool 28.4% 18.0% Pending
16 Dominic Calvert Lewin Leeds United Manchester United 27.4% 23.1% Pending
17 Yoane Wissa Newcastle United Aston Villa 26.4% 24.5% Pending
19 Benjamin Sesko Manchester United Leeds United 25.4% 33.2% Pending
20 Omar Marmoush Tottenham Hotspur Coventry City 25.4% 26.7% Pending
15 Jack Hinshelwood Brighton & Hove Albion Crystal Palace 25.0% 19.1% Pending
17 Bruno Fernandes Manchester United Leeds United 24.8% 22.3% Pending
19 Justin Kluivert AFC Bournemouth Sunderland 24.4% 16.9% Pending
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.