ICE Hockey League 2022/23 — results, standings and analytics

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

Scheduled games 0

No scheduled games left for this selection. The model accuracy below still covers the season's completed games.

Predicted vs actual 336

211 hit · 125 missed · 15 exact

Winner called right62.8%211 of 336 games

Exact scoreline154.5% of games

Mean goal error±1.75on the total goals in a game

Mean prediction54.1%home actually won 55.4%

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

21 Apr 2023, 19:30	HCBvsRBS	53%	2.4 – 2.2	2:2	1:2	Miss	-1.5
18 Apr 2023, 19:30	RBSvsHCB	57%	2.5 – 2.1	2:2	3:4	Miss	+2.5
16 Apr 2023, 17:30	HCBvsRBS	52%	2.3 – 2.2	2:2	4:3 OT	Hit	+2.6
14 Apr 2023, 19:30	RBSvsHCB	56%	2.4 – 2.1	2:2	3:0	Hit	-1.5
11 Apr 2023, 19:30	HCBvsRBS	55%	2.4 – 2.1	2:2	1:4	Miss	+0.5
08 Apr 2023, 19:30	RBSvsHCB	55%	2.4 – 2.2	2:2	1:0	Hit	-3.6
06 Apr 2023, 19:30	HCBvsRBS	55%	2.5 – 2.2	2:2	1:0	Hit	-3.7
02 Apr 2023, 18:00	HCBvsVIC	71%	3.6 – 2.2	3:2	3:2	Hit★	-0.8
02 Apr 2023, 17:30	RBSvsKAC	68%	2.9 – 1.9	2:1	4:0	Hit	-0.8
31 Mar 2023, 19:30	KACvsRBS	42%	2.1 – 2.6	2:2	1:3	Hit	-0.7
31 Mar 2023, 19:15	VICvsHCB	40%	2.5 – 3.1	2:3	2:5	Hit	+1.4
28 Mar 2023, 19:30	HCBvsVIC	71%	3.6 – 2.2	3:2	1:2	Miss	-2.8
28 Mar 2023, 19:15	RBSvsKAC	66%	2.8 – 1.9	2:1	5:1	Hit	+1.2
26 Mar 2023, 17:30	KACvsRBS	41%	2.1 – 2.6	2:2	6:2	Miss	+3.4
26 Mar 2023, 17:30	VICvsHCB	39%	2.5 – 3.2	2:3	2:3	Hit★	-0.7
24 Mar 2023, 19:45	HCBvsVIC	71%	3.6 – 2.3	3:2	2:1 OT	Hit	-2.9
24 Mar 2023, 19:30	RBSvsKAC	66%	2.8 – 1.9	2:1	5:1	Hit	+1.4
21 Mar 2023, 19:30	HCBvsBWL	76%	3.6 – 1.9	3:1	3:2 OT	Hit	-0.4
19 Mar 2023, 17:30	BWLvsHCB	31%	2.1 – 3.3	2:3	2:1 OT	Miss	-2.3
19 Mar 2023, 17:30	VICvsHCI	53%	3.6 – 3.5	3:3	5:1	Hit	-1.1
17 Mar 2023, 19:45	HCBvsBWL	75%	3.5 – 1.9	3:1	7:1	Hit	+2.6
17 Mar 2023, 19:30	VSVvsKAC	55%	3.2 – 2.9	3:2	2:3 OT	Miss	-1.1
17 Mar 2023, 19:15	HCIvsVIC	60%	3.9 – 3.2	3:3	1:4	Miss	-2.2
14 Mar 2023, 19:30	KACvsVSV	53%	3.2 – 3.0	3:2	3:1	Hit	-2.1
14 Mar 2023, 19:15	AVSvsRBS	38%	1.9 – 2.6	1:2	1:6	Hit	+2.5
14 Mar 2023, 19:15	BWLvsHCB	35%	2.2 – 3.1	2:3	1:5	Hit	+0.8
14 Mar 2023, 19:15	VICvsHCI	52%	3.7 – 3.6	3:3	1:2 OT	Miss	-4.3
12 Mar 2023, 18:00	HCBvsBWL	74%	3.5 – 1.9	3:1	1:2	Miss	-2.4
12 Mar 2023, 17:30	HCIvsVIC	62%	4.1 – 3.2	4:3	2:5	Miss	-0.3
12 Mar 2023, 17:30	VSVvsKAC	58%	3.3 – 2.8	3:2	3:4	Miss	+0.9
12 Mar 2023, 16:30	RBSvsAVS	70%	2.9 – 1.8	2:1	2:1 OT	Hit★	-1.7
10 Mar 2023, 19:30	VICvsHCI	53%	3.8 – 3.6	3:3	0:4	Miss	-3.3
10 Mar 2023, 19:15	AVSvsRBS	40%	2.0 – 2.6	2:2	1:2	Hit	-1.6
10 Mar 2023, 19:15	BWLvsHCB	34%	2.2 – 3.2	2:3	2:1	Miss	-2.3
10 Mar 2023, 19:15	KACvsVSV	56%	3.3 – 2.9	3:2	0:4	Miss	-2.1
07 Mar 2023, 19:45	HCBvsBWL	75%	3.6 – 2.0	3:1	2:0	Hit	-3.6
07 Mar 2023, 19:30	VSVvsKAC	58%	3.4 – 2.8	3:2	0:4	Miss	-2.2
07 Mar 2023, 19:15	RBSvsAVS	70%	2.9 – 1.8	2:1	3:2	Hit	+0.3
07 Mar 2023, 19:15	HCIvsVIC	62%	4.0 – 3.2	3:3	4:6	Miss	+2.8
05 Mar 2023, 17:30	BWLvsG99	63%	2.9 – 2.1	2:2	3:0	Hit	-2.0
03 Mar 2023, 19:45	ASHvsAVS	51%	2.8 – 2.7	2:2	4:5	Miss	+3.5
03 Mar 2023, 19:30	G99vsBWL	51%	2.4 – 2.4	2:2	2:6	Miss	+3.2
28 Feb 2023, 19:30	BWLvsG99	62%	2.8 – 2.1	2:2	2:4	Miss	+1.1
28 Feb 2023, 19:15	AVSvsASH	59%	3.1 – 2.5	3:2	4:0	Hit	-1.6
26 Feb 2023, 17:30	G99vsPIV	70%	3.1 – 1.9	3:1	4:0	Hit	-1.0
26 Feb 2023, 17:30	HCPvsOLL	71%	3.6 – 2.2	3:2	7:2	Hit	+3.2
26 Feb 2023, 17:30	HCBvsRBS	56%	2.6 – 2.2	2:2	4:3	Hit	+2.2
26 Feb 2023, 17:30	ASHvsKAC	44%	2.7 – 3.0	2:3	5:1	Miss	+0.3
26 Feb 2023, 17:30	BWLvsAVS	51%	2.5 – 2.5	2:2	4:2	Hit	+1.0
26 Feb 2023, 17:30	VICvsHCI	50%	3.6 – 3.5	3:3	5:3	Hit	+0.9

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

KACvsPIV
11 Dec 2022, 16:00 · predicted 81% home
1:3away won
PIVvsRBS
29 Nov 2022, 19:30 · predicted 20% home
2:1 SOhome won
HCIvsBWL
01 Oct 2022, 19:15 · predicted 80% home
2:5away won
PIVvsHCB
23 Dec 2022, 19:30 · predicted 22% home
5:4home won
HCIvsG99
17 Feb 2023, 19:15 · predicted 78% home
2:4away won

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

Best calls

RBSvsPIV
27 Jan 2023, 19:15 · predicted 89% home
5:1as predicted
HCBvsPIV
01 Jan 2023, 18:00 · predicted 88% home
4:2as predicted
RBSvsPIV
18 Nov 2022, 19:15 · predicted 87% home
6:1as predicted
HCBvsOLL
14 Feb 2023, 19:45 · predicted 87% home
5:1as predicted
HCIvsPIV
30 Dec 2022, 19:15 · predicted 86% home
5:1as 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.

How well does this model do?

336 games scored

Winner called right62.8%home-only baseline 55.4%

Brier score0.226baseline 0.249 · lower is better

Log loss0.642baseline 0.692

Beats the baseline by0.023Brier points of skill

Total-goals error±1.75mean absolute error per game

Exact scoreline4.5%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	50.0%	66.7%
24	50.0%	54.2%
36	55.6%	55.6%
48	47.9%	58.3%
60	51.7%	58.3%
72	52.8%	56.9%
84	54.8%	54.8%
96	55.2%	55.2%
108	56.5%	56.5%
120	56.7%	55.8%
132	57.6%	57.6%
144	55.6%	58.3%
156	56.4%	59.6%
168	56.5%	58.9%
180	56.7%	60.0%
192	57.3%	59.9%
204	57.8%	60.8%
216	57.9%	60.6%
228	57.9%	61.4%
240	58.3%	62.1%
252	56.7%	61.5%
264	56.8%	62.1%
276	55.4%	62.3%
288	55.9%	63.9%
300	56.0%	63.3%
312	54.8%	62.5%
324	55.6%	62.7%
336	55.4%	62.8%

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
20–30	25%	41%	17
30–40	36%	39%	54
40–50	45%	42%	59
50–60	55%	51%	75
60–70	65%	67%	70
70–80	74%	79%	43
80–90	83%	87%	15

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 2021/22 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 — and read the accuracy panel above before trusting any single number.