Model
What a model must beat — mean absolute error, percentage points
Training set
|
Rows
Played matches where both sides had enough prior matches to form an average
|
0 |
|
Split
Chronological, never random
|
0 / 0 |
min_history is 3 — every row needs both
sides to have 3 earlier matches to average, which nobody has
until about matchday 4. Nothing is broken; the season is
young. The figures below are what the model will use once there is something
to fit.
training.season in config.yaml.
Feature inventory — 48 columns the model would use, taken from the fixture side since there is no training set yet
Minutes spent ahead, level and behind are deliberately not here. They are only known after the whistle, so using them to predict possession would be leakage. They are stored for explaining errors instead: a match settled early is inherently less predictable, because the leading side stops trying to keep the ball.
Possession (16)
home_poss_l5away_poss_l5home_poss_l10away_poss_l10home_poss_l20away_poss_l20home_poss_home_l5away_poss_away_l5home_pass_acc_l5away_pass_acc_l5home_passes_l5away_passes_l5poss_gap_l5poss_gap_l10poss_naive_l5h2h_home_poss_avg
Attacking form (7)
home_xg_l5home_xgd_l5home_xg_l10away_xg_l5away_xgd_l5away_xg_l10h2h_home_xg_avg
Defensive form (4)
home_xga_l5home_xga_l10away_xga_l5away_xga_l10
Points and results (6)
home_ppg_l5home_ppg_l10away_ppg_l5away_ppg_l10ppg_edge_l5h2h_home_ppg
Volume (4)
home_sot_l5home_corners_l5away_sot_l5away_corners_l5
Matchup edges (3)
xgd_edge_l5home_attack_vs_away_defenceaway_attack_vs_home_defence
Head to head (2)
h2h_meetingsh2h_home_goals_avg
Schedule and fatigue (2)
home_days_restaway_days_rest
Other (4)
home_matches_beforehome_finishing_gapaway_matches_beforeaway_finishing_gap
Stake guidance — open lines, rated out of 10
Two separate things have to be true before staking much: the edge must be large, and the model must have shown it can find real edges. The first is arithmetic; the second is a track record. The rating is the smaller of the two, so a big edge from a model with no record scores low — correctly. It is 10 settled bets in, so the ceiling is low for a while yet.
| Kickoff | Match | Line is about | Line | Under | Over | Model | Market | Bet | Edge | Stake | Why |
|---|---|---|---|---|---|---|---|---|---|---|---|
| 13 Sep 15:30 | ELV v FCB | FC Bayern München | 65.0 | 1.85 | 1.85 | 60.0%* | 50% over | UNDER | +18.3% | 2/10 | edge alone suggests 4/10, capped at 2 by a very thin track record (10 settled) |
* 1 row here did not come from a fitted model. This league has too little history to fit one, so the figure is the naive midpoint: the side's own recent possession averaged against what its opponent concedes — on as few as two matches each. That formula shrinks towards 50 by construction, so it understates a mismatch. A strong side away at a weak one reads too low, and the edge it implies against a bookmaker's line can point the wrong way entirely. The Bet, Edge and Stake columns on these rows are arithmetic, not a tested prediction.
0/10 means the price is against you — not a close call, a bet to skip. Anything above that is a fraction of what you would stake at full confidence, and quarter-Kelly is treated as the ceiling even at 10/10, because Kelly assumes the probability is exactly right and this one is an estimate.
Next fixtures — with the naive prediction to beat
| Kickoff | Match | Home form | Away form | Gap | Naive home poss |
|---|---|---|---|---|---|
| 13 Sep, 15:30 | SV Elversberg v FC Bayern München | 45.0% | 67.0% | -22.0 | 39.0% |
| 18 Sep, 18:30 | FC Bayern München v 1. FC Union Berlin | 67.0% | 48.0% | +19.0 | 59.5% |
| 19 Sep, 13:30 | Hamburger SV v 1. FC Köln | 46.3% | 47.3% | -1.0 | 49.5% |
| 19 Sep, 13:30 | SV Werder Bremen v FC Augsburg | 42.7% | 42.7% | +0.0 | 50.0% |
| 19 Sep, 13:30 | Eintracht Frankfurt v Sport-Club Freiburg | 53.3% | 52.7% | +0.7 | 50.3% |
| 19 Sep, 13:30 | Borussia Mönchengladbach v 1. FSV Mainz 05 | 46.7% | 49.7% | -3.0 | 48.5% |
| 19 Sep, 16:30 | VfB Stuttgart v Borussia Dortmund | 49.3% | 50.3% | -1.0 | 49.5% |
| 20 Sep, 13:30 | Bayer 04 Leverkusen v RB Leipzig | 60.7% | 58.7% | +2.0 | 51.0% |
| 20 Sep, 15:30 | FC Schalke 04 v SV Elversberg | 39.3% | 45.0% | -5.7 | 47.2% |
| 20 Sep, 17:30 | SC Paderborn 07 v TSG Hoffenheim | 52.7% | 51.7% | +1.0 | 50.5% |