A machine learning model that predicts the winners of AFL football matches
Correct tips
137
Accuracy
66.2%
Top percentile of AFL footy tipping
3.1%
Welcome to the Footy Forest. Here you’ll find predictions, details on how the model is performing, rankings of each team and occasional statistical analyses of AFL footy and other sports.
Tips based on teams selected on Thursday night | ||||||||
---|---|---|---|---|---|---|---|---|
Home | Away | Relative advantage to the home team1 | Predicted winner | Probability | Margin | |||
Power | Venue exp | Travel | Team rating | |||||
Melbourne | Collingwood | -0.9 | -9.9 | 0.0 | 24.8 | Melbourne | 58 | 8 |
Geelong Cats | West Coast Eagles | 51.8 | 90.1 | 73.8 | 18.0 | Geelong Cats | 82 | 37 |
Richmond | Gold Coast Suns | -40.9 | 77.7 | 37.1 | -5.6 | Gold Coast Suns | 72 | 24 |
Hawthorn | North Melbourne | 69.5 | 74.3 | 0.0 | 47.6 | Hawthorn | 82 | 37 |
Brisbane Lions | Essendon | 34.5 | 82.7 | 38.0 | 15.0 | Brisbane Lions | 81 | 35 |
Sydney Swans | Adelaide Crows | 17.7 | 90.0 | 32.3 | 5.2 | Sydney Swans | 78 | 31 |
Western Bulldogs | GWS Giants | 6.7 | 14.9 | 18.5 | -23.8 | Western Bulldogs | 73 | 25 |
Carlton | St Kilda | 8.5 | -9.9 | 0.0 | 30.5 | Carlton | 67 | 19 |
Fremantle | Port Adelaide | -7.3 | 85.1 | 58.8 | 0.1 | Fremantle | 62 | 13 |
1This is the difference between the teams where 100 is the highest since 2015 and -100 is the lowest |