Match ☆ 18 Sep 2016 · 13:00 UTC
SWE · Allsvenskan · 2016
View head-to-head record →
Betting odds
Closing odds (last odds before kick-off)
Pinnacle home win odds 1.35
Pinnacle draw odds 5.46
Pinnacle away win odds 9.78
Market maximum home win odds 1.35
Market maximum draw odds 6.1
Market maximum away win odds 11.89
Market average home win odds 1.31
Market average draw odds 5.19
Market average away win odds 9.05
The models what they said before kick-off
Draw predictor · this site's own figures
Figure AIK Fotboll Gefle IF
N — no-draw runmatches in a row without a draw 2 0
Max Nthis team's longest run ever 20 19
E — draw debtexpected draws over the current run 0.41 0.00
p50 — last 50draw rate over its last 50 matches 18.0% 18.0%
p100 — last 100draw rate over its last 100 matches 22.0% 23.0%
Draw % — all timeshare of every match drawn 24.4% 25.4%
Σ Nboth sides' runs added 2
Σ Eboth sides' draw debt added 0.41

These are the figures that held before kick-off: each side's record over every match it had played before 18 Sep 2016, computed exactly as the predictor computes today's. Draw score and rank are left out: both place a team against the whole field, and the field can only be scored as it stands now.

Team strength · Elo
AIK Fotboll 1,792 after: 1,795
Gefle IF 1,534 after: 1,531
Rating gap +323 home advantage included
Draws at this gap 14.0% 300+ · 22,504 matches
Goals model · Dixon-Coles
Expected goals 2.22 – 0.72 home – away
Home win 71.2%
Draw 18.6% every level score added up
Away win 10.2%
Both together · the blend
Blended draw chance 17.4% 75% goals model · 25% Elo gap
Goals model said 18.6% form only
This Elo gap said 14.0% strength only

The mix is the one that scored best over 544,576 matches — the two are averaged on the log-odds scale, not simply added.

The regression · the logistic model
Logistic draw chance 14.2% five signals, then recalibrated
95% band 13.1% – 14.2% how unsure the fit is, not the match
The blend says 17.4% the older published reading

A regression over five signals — the goals model, the draw rate at this Elo gap, the expected goals in the fixture and the competition's own base draw rate — with an isotonic map on top to put the level back where reality is. Held out on a decade it never saw it beat the blend above, which is why both are shown here while one is chosen. Unlike the two readings above it, this one is not leak-free: the model was fitted on all of history, this match included, so for a played match it is a description rather than a prediction.

Both figures are what the models knew before this match — neither ever reads the result it is describing, so they can be compared with what actually happened. Measured over 160,869 priced matches the goals model is slightly worse than the bookmakers (how it is scored), so a high draw chance means an even, low-scoring match rather than value. Descriptive statistics, not betting advice.