How the AFL model works
We project each player's disposals against the line and publish only the bets the data rewards.
See the multi-sport framework—
Strong win rate
recorded · graded after each round
6
Inputs per prediction
weighted & blended
Every tool, free and Pro
The graded record and injury board are free; the model-derived boards and research are Pro.
What goes into a prediction
Every line is a weighted blend of six inputs around the player's baseline.
2026 formblendedCurrent-season disposal average - weighted higher as games build up.
2025 baselineblendedPrior full season, for a stable anchor early in the year.
Opponent±How many disposals this opponent concedes to the position vs league average.
Time on ground×More minutes means more disposals - scaled to expected TOG.
Role / CBA×Centre-bounce attendance lift for midfielders in the engine room.
Style + conditions×Run-and-carry vs contested, plus wet-weather and roof-venue adjustments.
Confidence tiers
Edge alone isn't enough. We divide edge by the player's volatility (Edge/Vol) to score signal vs noise.
High Conviction
E/V ≥ 1.4× threshold
Edge is large relative to the player's usual variance - at least 1.4 times the position threshold below.
BET
E/V ≥ threshold
Real edge that clears the position threshold: 0.50 for MID/DEF, 0.55 for RUCK - raised by 0.10 for high-volatility players (σ > 6) and 0.25 for extreme volatility (σ > 8).
SKIP
below threshold
A lean, but inside normal variance - not published. At most two picks per team-position combination make the board.
Reading the Round Slate
What each column and marker on the Round Slate board means.
EdgeModel projection minus the line.
L5Last-5 disposal average, over games actually played before this round. Fewer games than the label shows the real count beside it (e.g. "25.7 3g"); under 4 games shows n/a instead of a figure.
VolLast-10 game standard deviation, same sample rules as L5.
E/Vol|Edge| / Vol - risk-adjusted edge. This is what the confidence tiers above are built from.
L5 vs lineHow many games in that same sample hit the pick side.
vs OppShare of games by players in the same position bucket, against this opponent, that went over the line this season. A * means the sample was thin so all positions are pooled - a rough guide only.
!The call is contradicted by every game in its own shown sample.
TAGLikely tagged - model suppression shows on hover.
BOOSTUsage lift if the named teammate is out.
HELDA candidate the guardrail held this round; the reason shows on hover so nothing silently vanishes.
Green / redOver / under. Click a player on the board for their full card.
What we publish (and thin weeks)
The model flags 100+ edges a round. These rules cut it to the picks you see.
OVERs: High Conviction only
BET and LEAN OVERs lose money at standard vig in our data, so only HC OVERs are published.
UNDERs: stricter cut
UNDERs work at every tier but pass a tougher line, edge and tough-defence filter - the UnderTaker.
Some weeks are quiet on purpose
A handful of picks means the model is declining bad bets - not that nothing happened.
By position
MID / DEFpublishedMost efficient markets and where the model performs best. Standard edge thresholds.
FWDanalysis onlyModel accuracy is ~38% - shown for context, never bet.
RUCKconservativeDisposals are a weak proxy for ruck impact, so the bar is high.
What it doesn't do
Where the edge comes from matters - so does where it stops.
Late injury & team newsWe don't scrape selections - always check the official team list before betting.
ForwardsFWD disposal prediction is a known weak spot, so FWDs are excluded from picks.
Early-season noiseOpponent data is thin before Round 6, so its influence is dialled back.
It's decision supportThe model finds statistical edges - it isn't a guarantee on any single bet.