ICE Hockey League 2024/25 — predictions, results and standings

Some data is unavailable right now (teams). Panels that depend on it are hidden.

The model has called 63% of 336 2024/25 games right · always picking the home side: 55%

No scheduled games left for this selection. The sections below cover the season's completed games.

Predicted vs actual336 finished games

Predicted vs actual 336

210 hit · 126 missed · 17 exact

Winner called right62.5%210 of 336 games

Exact scoreline175.1% of games

Mean goal error±2.01on the total goals in a game

Mean prediction54.0%home actually won 54.8%

Every finished game with the prediction it had beforehand, sortable by any column

11 Apr 2025, 19:30	RBSvsKAC	55%	3.0 – 2.7	3:2	4:0	Hit	-1.8
08 Apr 2025, 19:30	KACvsRBS	57%	3.1 – 2.7	3:2	1:3	Miss	-1.8
06 Apr 2025, 17:30	RBSvsKAC	52%	3.0 – 2.9	2:2	4:0	Hit	-1.8
04 Apr 2025, 19:30	KACvsRBS	60%	3.3 – 2.7	3:2	1:2 OT	Miss	-3.0
01 Apr 2025, 19:30	KACvsBWL	69%	3.6 – 2.4	3:2	2:0	Hit	-4.0
30 Mar 2025, 17:30	BWLvsKAC	39%	2.7 – 3.3	2:3	2:0	Miss	-4.0
28 Mar 2025, 19:30	KACvsBWL	70%	3.7 – 2.4	3:2	5:3	Hit	+2.0
28 Mar 2025, 19:15	RBSvsHCB	56%	3.0 – 2.6	2:2	4:2	Hit	+0.5
25 Mar 2025, 19:45	HCBvsRBS	54%	2.9 – 2.7	2:2	2:3 OT	Miss	-0.6
25 Mar 2025, 19:30	BWLvsKAC	39%	2.6 – 3.4	2:3	3:1	Miss	-2.0
23 Mar 2025, 17:30	KACvsBWL	69%	3.7 – 2.4	3:2	5:2	Hit	+1.0
23 Mar 2025, 16:30	RBSvsHCB	56%	3.0 – 2.6	2:2	2:3 OT	Miss	-0.6
21 Mar 2025, 19:45	HCBvsRBS	54%	2.9 – 2.7	2:2	2:3	Miss	-0.6
21 Mar 2025, 19:30	BWLvsKAC	41%	2.7 – 3.3	2:3	2:4	Hit	+0.1
18 Mar 2025, 19:30	RBSvsHCB	55%	3.0 – 2.7	2:2	3:1	Hit	-1.6
18 Mar 2025, 19:15	KACvsBWL	70%	3.7 – 2.4	3:2	2:3 OT	Miss	-1.1
16 Mar 2025, 17:30	BWLvsG99	52%	2.9 – 2.8	2:2	3:2 OT	Hit	-0.7
14 Mar 2025, 19:45	HCPvsKAC	30%	2.5 – 3.7	2:3	1:3	Hit	-2.2
14 Mar 2025, 19:30	G99vsBWL	59%	3.1 – 2.6	3:2	3:4 OT	Miss	+1.3
14 Mar 2025, 19:15	VSVvsHCB	45%	2.9 – 3.2	2:3	2:4	Hit	-0.1
11 Mar 2025, 19:45	HCBvsVSV	63%	3.5 – 2.6	3:2	6:1	Hit	+0.9
11 Mar 2025, 19:30	BWLvsG99	51%	2.9 – 2.9	2:2	2:1 OT	Hit	-2.8
11 Mar 2025, 19:15	KACvsHCP	79%	4.2 – 2.2	4:2	2:4	Miss	-0.4
09 Mar 2025, 18:00	HCPvsKAC	30%	2.5 – 3.8	2:3	1:4	Hit	-1.2
09 Mar 2025, 17:30	VSVvsHCB	46%	2.9 – 3.1	2:3	5:3	Miss	+2.0
09 Mar 2025, 16:00	AVSvsRBS	47%	2.5 – 2.7	2:2	3:6	Hit	+3.8
08 Mar 2025, 18:30	G99vsBWL	59%	3.2 – 2.6	3:2	5:4 OT	Hit	+3.3
07 Mar 2025, 19:45	HCBvsVSV	64%	3.5 – 2.6	3:2	3:1	Hit	-2.1
07 Mar 2025, 19:15	RBSvsAVS	62%	3.0 – 2.3	3:2	2:0	Hit	-3.4
07 Mar 2025, 19:15	KACvsHCP	77%	4.1 – 2.2	4:2	6:2	Hit	+1.7
06 Mar 2025, 19:30	BWLvsG99	50%	2.9 – 2.9	2:2	3:2 OT	Hit	-0.7
04 Mar 2025, 19:30	HCPvsKAC	30%	2.5 – 3.8	2:3	3:0	Miss	-3.3
04 Mar 2025, 19:15	AVSvsRBS	48%	2.7 – 2.8	2:2	0:1	Hit	-4.5
04 Mar 2025, 19:15	VSVvsHCB	46%	2.9 – 3.1	2:3	4:3 OT	Miss	+1.0
04 Mar 2025, 18:30	G99vsBWL	59%	3.2 – 2.6	3:2	3:2 OT	Hit★	-0.8
02 Mar 2025, 18:00	HCBvsVSV	62%	3.4 – 2.6	3:2	4:1	Hit	-1.1
02 Mar 2025, 17:30	BWLvsG99	52%	2.8 – 2.6	2:2	6:9	Miss	+9.6
02 Mar 2025, 17:30	KACvsHCP	77%	4.2 – 2.3	4:2	4:0	Hit	-2.5
02 Mar 2025, 16:30	RBSvsAVS	61%	3.1 – 2.4	3:2	3:2	Hit★	-0.5
28 Feb 2025, 19:30	AVSvsVIC	69%	3.0 – 1.9	3:1	3:2	Hit	+0.0
25 Feb 2025, 19:45	HCPvsOLL	53%	2.9 – 2.8	2:2	2:0	Hit	-3.7
25 Feb 2025, 19:15	VICvsAVS	38%	2.2 – 2.8	2:2	1:0	Miss	-4.0
23 Feb 2025, 18:00	OLLvsHCP	57%	3.1 – 2.7	3:2	1:2 OT	Miss	-2.8
23 Feb 2025, 15:30	AVSvsVIC	69%	3.2 – 2.0	3:1	2:1	Hit	-2.2
21 Feb 2025, 19:15	HCBvsHCI	89%	4.7 – 1.6	4:1	9:2	Hit	+4.7
21 Feb 2025, 19:15	BWLvsPIV	69%	3.3 – 2.1	3:2	4:1	Hit	-0.4
21 Feb 2025, 19:15	AVSvsRBS	48%	2.7 – 2.8	2:2	3:4	Hit	+1.4
21 Feb 2025, 19:15	VSVvsASH	76%	4.5 – 2.7	4:2	8:3	Hit	+3.8
21 Feb 2025, 19:15	KACvsHCP	77%	4.3 – 2.4	4:2	2:0	Hit	-4.8
21 Feb 2025, 19:15	VICvsOLL	50%	2.6 – 2.6	2:2	1:6	Hit	+1.8

Showing 50 of 336 rows. Sort or filter to narrow the list.

Each row's prediction was built from the games played before that date only — nothing after it. Sort by Goals Δ or Call to find where the model went wrong. A ★ marks a game whose exact scoreline it also got right.

Biggest upsets

HCBvsASH
04 Oct 2024, 20:30 · predicted 89% home
2:8away won
RBSvsHCP
11 Oct 2024, 19:15 · predicted 83% home
5:6 SOaway won
RBSvsPIV
28 Dec 2024, 19:15 · predicted 81% home
1:6away won
KACvsHCI
01 Nov 2024, 19:15 · predicted 81% home
1:4away won
BWLvsASH
01 Oct 2024, 19:15 · predicted 19% home
8:2home won

Games where the model was most confident in the side that lost.

Best calls

G99vsBWL
29 Sept 2024, 17:30 · predicted 96% home
2:0as predicted
KACvsHCI
26 Jan 2025, 16:00 · predicted 91% home
11:3as predicted
HCBvsHCI
21 Feb 2025, 19:15 · predicted 89% home
9:2as predicted
KACvsVSV
29 Sept 2024, 17:30 · predicted 88% home
5:3as predicted
HCBvsHCI
20 Oct 2024, 18:00 · predicted 88% home
4:2as predicted

Confident calls that came in. Note these are cheap to collect — a good model should have many of them, which is why the upsets matter more.

Accuracy and calibrationBrier 0.231

How well does this model do?

336 games scored

Winner called right62.5%home-only baseline 54.8%

Brier score0.231baseline 0.250 · lower is better

Log loss0.653baseline 0.694

Beats the baseline by0.019Brier points of skill

Total-goals error±2.01mean absolute error per game

Exact scoreline5.1%hit rate on the likeliest score

Accuracy as the season went onCumulative share of games called right, against picking the home side every time

Home-only baseline
Model

Table view

Games scored	Home-only baseline	Model
12	66.7%	58.3%
24	54.2%	54.2%
36	58.3%	50.0%
48	54.2%	56.3%
60	46.7%	55.0%
72	47.2%	54.2%
84	47.6%	56.0%
96	44.8%	55.2%
108	46.3%	55.6%
120	47.5%	56.7%
132	49.2%	59.1%
144	48.6%	60.4%
156	48.7%	59.6%
168	50.6%	58.3%
180	49.4%	58.9%
192	50.0%	60.4%
204	50.0%	60.8%
216	50.9%	60.6%
228	51.3%	61.0%
240	52.1%	60.0%
252	52.8%	60.3%
264	52.7%	60.6%
276	52.5%	61.2%
288	53.1%	61.8%
300	54.0%	62.3%
312	55.1%	62.8%
324	54.3%	63.0%
336	54.8%	62.5%

Both lines are cumulative, so they settle as the sample grows. The gap between them is the model's edge over the naive pick.

CalibrationWhen the model says 70%, does the home side win 70% of the time?

Predicted
Actual

Table view

Predicted home win %	Predicted	Actual	Games
10–20	18%	10%	10
20–30	27%	33%	21
30–40	35%	51%	45
40–50	45%	41%	64
50–60	55%	55%	64
60–70	65%	65%	69
70–80	75%	71%	42
80–90	84%	79%	19

The two lines tracking each other means the probabilities can be taken at face value. Where "actual" sits above "predicted", the model is under-confident in the home side; below, it is over-confident. Check the game count before reading much into a bucket — the extremes hold far fewer games than the middle. Buckets with fewer than five games are left out.

Every game is predicted using only the games played before it — a walk-forward test, so these are the numbers the model would really have produced. The baseline is "always back the home side", priced at the home-win rate known at the time. Team strengths start from the 2023/24 final table.

How the prediction works

Each team gets an attack and a defence multiplier from the goals it has scored and conceded, measured against the league average.
A fixture's expected goals are the league's home (or away) scoring rate times the attacking team's attack times the defending team's defence — so home advantage comes out of fitting home and away separately, not from a bonus added on top.
Both sides' goals are then treated as independent Poisson draws, which gives a probability for every scoreline rather than one guess, and from that the win, overtime and exact-score numbers.
Rates are shrunk toward the prior with six games of weight, so an early 7-1 win does not make a team look unbeatable. This is why fixtures are marked low confidence until both teams have played a few games.
Overtime and shootouts are treated as a coin flip. The feeds carry nothing that reliably predicts a shootout winner, and pretending otherwise would just be noise.

Goal models like this one capture scoring rates, not injuries, suspensions, travel, goalie rotation or roster changes. Treat the probabilities as a calibrated baseline, not a forecast.