Motion-blurred skater in a San Jose Sharks sweater

Breakdown · SJS at WPG

Sharks pull away from the Jets

FinalThu, Apr 16

The verdict · earned

The Sharks earned it — the game and the expected-goals battle both.

SJS 6 · WPG 1

◆ By the ModelJul 12, 12:05 PMxG: xgboost-0.758Edited for clarityDrafted from NHL play-by-play by Backcheck's model, worded for clarity by an AI editor that may not change a number. Nobody at Backcheck was at the rink. How this works

The Sharks' 6-1 victory masks a more revealing story: San Jose overperformed their expected goals by 2.00, while Winnipeg underperformed by 2.05—a four-goal swing between what the numbers said should happen and what the scoreboard showed.

Underlying play told a different tale. The Sharks controlled 57% of 5v5 expected goals (4.00–3.05) despite outshooting Winnipeg only 33–27, generating higher-quality looks at 0.073 xG per shot versus Winnipeg's 0.052. The Jets squandered their opportunities—they had eight high-danger chances to San Jose's three, yet scored just once.

A. Nedeljkovic (SJS) took over the show, stopping 26 of 27 shots for a 0.963 save percentage and a +2.05 goal differential against expected outcomes. E. Comrie (WPG) suffered the opposite: stopped 27 of 33 for a 0.818 save percentage and a –2.00 gap.

The Sharks were relentless in execution. They scored three goals on 26 rush chances and generated seven rebound opportunities, converting three. Macklin Celebrini's snap shot from the high slot at 1:14 of the third period exemplified their ability to finish from dangerous areas, turning San Jose's underlying control into actual runs.

Three Stars:

#3 J. Klingberg (SJS) — 3A in 20:54
#71 M. Celebrini (SJS) — 1G, 2A in 14:41
#72 W. Eklund (SJS) — 1G, 2A in 14:24

The breakdown in twelve frames

Swipe it

Every number is from this page

Final · Apr 16

SJS

WPG

Sharks pull away from the Jets

Chances 4.0 – 3.0Did they deserve it? →

Did they deserve it?

The Sharks earned this one.

Expected goals · chance value

SJS

4.00

WPG

3.05

57% of the chances43%

The board read SJS 6, WPG 1. The chances read SJS 4.0, WPG 3.0.

Our xG model · NHL play-by-play · all situations

Luck check

SJS

+2.0

goals above expected

SJS4.00 expected · 6 scored

Expected

Scored

WPG3.05 expected · 1 scored

Expected

Scored

The Sharks scored 2.0 more than their chances were worth. That does not repeat.

PDO = sh% + sv% · drifts to 1.000 over a season

Every goal, in order

P1 03:28WPGC. Koepke0–1
P1 06:26SJSI. ChernyshovPP1–1
P1 16:54SJSW. Smith2–1
P2 05:51SJSC. Graf3–1
P2 18:01SJSM. Misa4–1
P2 19:55SJSW. Eklund5–1
P3 01:14SJSM. Celebrini6–1

NHL play-by-play · chance value from our xG model

Where the shots came from

SJS

47 shots

Final

96 shots

WPG

49 shots

SJS WPG GoalBigger dot · more dangerous look

shots · 6 in

shots · 1 in

Every unblocked shot · press play to replay it

Chances by danger

SJSWPG

1 / 8

1.95 xG

High danger

0 / 3

0.61 xG

5 / 11

1.29 xG

Medium

1 / 17

1.60 xG

0 / 36

0.76 xG

Low

0 / 39

0.84 xG

The Jets went 0 for 3 from the slot.

Danger tiers by our xG model · high ≥ 20% chance

In the net

A. Nedeljkovic

+2.0

SJS · 26/27

E. Comrie

−2.0

WPG · 27/33

The numbers, checked

BACKCHECK

Sharks pull away from the Jets

A model, not a newsroom. Every number on these frames comes from the NHL's play-by-play and our own models. Nothing was watched, guessed or heard from anyone.

Read the full breakdown

backcheckreport.com

01 / 08 · Final

Every goal, in order

How it happened

NHL play-by-play

1stshots 7–13

03:28WPGC. Koepke0–1
06:26SJSI. Chernyshovpower play(W. Eklund, M. Celebrini)1–1
16:54SJSW. Smith(M. Celebrini, J. Klingberg)2–1

2ndshots 16–7

05:51SJSC. Graf3–1
18:01SJSM. Misa(W. Eklund, J. Klingberg)4–1
19:55SJSW. Eklund(M. Ferraro, K. Sherwood)5–1

3rdshots 10–7

01:14SJSM. Celebrini(J. Klingberg, W. Smith)6–1

score reads SJS–WPG

Source · NHL play-by-play (api-web.nhle.com)

Process vs result

The numbers

XGBoost xG · NHL play-by-play

4.00

SJS chances

Goals their shots were worth

+2.0

Finishing

Goals above what those chances were worth

1.092

SJS puck luck

Above 1.000 — the bounces went their way

48.2%

Shot attempts

Under half — they were outshot

Split by club

Who controlled the game

4.00Expected goals3.05

SJS 57% of the chance quality

33Shots on goal27

8High-danger chances3

55All attempts (Corsi)59

Adjusted for score: SJS 44% · WPG 56%

Faceoffs · WPG won71%off60%neu39%def

Source · NHL play-by-play · XGBoost xG

How the game was won

The danger ladder

shotsgoalsexpected

High dangerslot & crease

SJS1 / 8 · 1.95 xG

WPG0 / 3 · 0.61 xG

Medium dangermid-range

SJS5 / 11 · 1.29 xG

WPG1 / 17 · 1.60 xG

Low dangerperimeter & point

SJS0 / 36 · 0.76 xG

WPG0 / 39 · 0.84 xG

SJS went 5-for-11 from medium danger on 1.29 expected goals — 3.7 above expected.

Source · Backcheck xG model · NHL play-by-play

The luck layer

Finishing vs expected

expectedactual

SJS

6 G · 4.00 xG · +2.0

WPG

1 G · 3.05 xG · -2.0

01234567

SJS finished +2.0 against expected, WPG -2.0.

Source · Backcheck xG model

Shot types · rush and rebound chancesopen +

What they shot — and what went in

Shot diet

goalsshots

SJS

WRIST3/24

SNAP3/11

SLAP0/4

TIP IN0/5

BACKHAND0/2

WRAP AROUND0/1

OTHER0/8

WPG

WRIST0/31

SNAP1/8

SLAP0/7

TIP IN0/0

BACKHAND0/3

WRAP AROUND0/0

OTHER0/10

SJS

WPG

Off the rush

3 G on 26

2.19 xG

1 G on 35

2.35 xG

Off rebounds

3 G on 7

1.44 xG

0 G on 2

0.05 xG

Wrist shots carried the volume: SJS went 3-for-24, WPG 0-for-31. SJS scored 3 of theirs off the rush.

Source · Backcheck xG model · NHL shot types

New to these numbers?

Two things happened in this game: who created the better chances, and who put the puck in the net. They are not the same thing, and this page separates them on purpose.

The one to watch is expected goals— the best single read on who deserved to win. When it disagrees with the scoreboard, that disagreement is usually the story. Nothing here is a projection; every figure is computed from this game's play-by-play. Full glossary →

xG: Expected goals. Every shot scored by how often that exact look goes in. 2.5 xG means the chances were worth about two and a half goals.
HD: High-danger chances — shots from the slot and the crease, where shots actually become goals.
Corsi: Every shot attempt, including the ones that missed or got blocked. A rough read on who had the puck.
Adj.: Score-adjusted. Teams that trail shoot more and teams that lead sit back, so this corrects the attempt count for the scoreboard.
GSAx: Goals saved above expected. A positive number means the goalie stopped more than an average goalie would have on those shots.
PDO: Shooting % plus save % — a luck gauge. It sits near 1.000 over a season, so a game far from it usually means the bounces decided it.

Shot by shot

In the net

Graded on goals saved above expected

A. Nedeljkovic

SJS · 26/27 · .963

+2.0

saved above expected

the night

By dangerG/attxGsaved

High danger0/30.6+0.6

Medium1/171.6+0.6

Low0/390.8+0.8

A+ ≥ +2.5 saved above expected · A ≥ +1.5 · B+ ≥ +0.75 · B ≥ +0.25 · C ≥ −0.25 · D ≥ −0.75 · F below −1.5

E. Comrie

WPG · 27/33 · .818

-2.0

saved above expected

the night

By dangerG/attxGsaved

High danger1/81.9+0.9

Medium5/111.3-3.7

Low0/360.8+0.8

A+ ≥ +2.5 saved above expected · A ≥ +1.5 · B+ ≥ +0.75 · B ≥ +0.25 · C ≥ −0.25 · D ≥ −0.75 · F below −1.5

96 shots · press play to watch the game back

Where the shots came from

NHL play-by-play coordinates

SJS

47 shots

Final

96 shots

WPG

49 shots

SJS WPG GoalBigger dot · more dangerous look

Each club shoots toward its own end — SJS left, WPG right — the way you would watch it. A dot's size is how dangerous the look was, from distance and angle; it is a proxy for shot quality, not the xG model the article is written from. Hover a dot for the shooter and the clock.

Ranked from the box score

Three stars

Points first

Three stars · computed, not voted

J. Klingberg

#3 · D · SJS

0 G · 3 A · 0 SOG · 20:54 on ice · +3

M. Celebrini

#71 · C · SJS

1 G · 2 A · 3 SOG · 14:41 on ice · +2

W. Eklund

#72 · L · SJS

1 G · 2 A · 3 SOG · 14:24 on ice · +2

Ranked from the box score — points first · Backcheck

What the model said beforehand

Before the game

Written Thu, Apr 16

Open the pre-game read

Written from the numbers

The read

Edited for clarity

◆ By the ModelJul 12, 11:57 AMEdited for clarityDrafted from NHL play-by-play by Backcheck's model, worded for clarity by an AI editor that may not change a number. Nobody at Backcheck was at the rink. How this works

San Jose and Winnipeg are essentially interchangeable. The model projects a 2.4–2.6 goal range favoring the Jets, with Winnipeg's win probability sitting at exactly 52%—as close to a true coin flip as the numbers offer.

On paper, both teams are built identically. San Jose and Winnipeg each carry 48.0% expected goals share at five-on-five; the Sharks edge the Corsi battle at 47.0% versus 49.0%, a difference that means nothing. Both teams register 0.998 PDO, suggesting neither has luck working for or against them. This is parity.

Winnipeg's recent form tilts slightly negative. The Jets are minus-7 in goal differential over their last ten games—not catastrophic, but enough to suggest some slippage.

The goaltending angle offers the only tactical wrinkle. E. Comrie starts on a back-to-back, which typically signals either a backup appearance or a fatigued starter. That's worth monitoring.

Pavol Regenda is likely out and marked inactive, removing San Jose's most electric option at five-on-five. Regenda was running 1.10 expected goals per 60 minutes with a 16.1% shooting rate, translating to five goals and one assist. Igor Chernyshov carries a lighter offensive touch at 0.91 xG/60 but has produced six goals and eight assists with a 15.0% clip—something to respect.

Winnipeg's attack runs through Kyle Connor, who has assembled 25 goals and 30 assists while maintaining 0.83 xG/60 and 13.0% shooting efficiency. Nino Niederreiter offers secondary punch: 0.87 xG/60, six goals, six assists, and the highest hard-on-goal conversion rate in this matchup at 8.6%. That asymmetry—Connor's volume versus Niederreiter's efficiency—may prove decisive if either team gets a handful of clean looks.

The defensive vulnerabilities here matter less than offensive execution. Winnipeg's Colin Miller and San Jose's Igor Chernyshov both carry weaknesses, but neither is likely to be tested enough to swing the game. This contest will be decided by which team converts its half-chances first.

Everything points to a tightly matched game that could plausibly swing either way. The model's 52% mark for Winnipeg reflects that reality. Respect the coin flip.

What the model said beforehand

The model's lean

WPG 52%

52%

WPG

Model favorite

48%

52%

SJS50WPG

WPG by 4 points of win probability — effectively a coin flip. Projected score SJS 2.4–2.6 WPG; 18% chance it's tied after 60.

Source · Backcheck Poisson projection · season scoring rates

Season rates · 5v5

Tale of the tape

NHL stats API · our xG

SJS← edge

edge →WPG

48.0%48.0%

47.0%49.0%

2.332.34

2.562.55

1.991.90

2.322.10

0.9980.998

WPG holds 5 of 6 process categories — and the luck row (0.998 vs 0.998) says WPG has been getting the bounces, which tends not to last.

Source · NHL stats API + our xG · 5v5

Form · Last 10

SJS

6-3-1

-4 GD · 2d rest

WPG

5-5-0

-7 GD · 1d rest

0.998

SJS PDO

Luck gauge · drifts to 1.000

0.998

WPG PDO

Luck gauge · drifts to 1.000

What decides it

Keys to the game

Things to watch

E. Comrie is on a back-to-back — watch for a backup start or a tired starter.
The Jets are underwater at -7 goal differential over their last 10.

Last game's lineup · confirmed at warm-up

Lineups

NHL box score

SJS

Expected in goal

A. Nedeljkovic

2 days rest.929 last start

Backup Yaroslav Askarov · -18.9 GSAx this season

No completed game on file for this club yet.

WPG

Expected in goal

E. Comrie

back-to-back.886 last start

Backup Connor Hellebuyck · +5.5 GSAx this season

Back-to-back: the backup often gets this one. Treat the starter as unconfirmed.

No completed game on file for this club yet.

Lineups are the players who dressed in each club's last game, with their minutes; clubs confirm tonight's at warm-up. Every player this preview names was in that lineup.

Computed danger · scouting

Players to watch

NHL stats API · our xG

SJS

Pavol Regenda5G 1A

1.10 xG/60 · 2 HD · 16.1% sh

Igor Chernyshov6G 8A

0.91 xG/60 · 1 HD · 15.0% sh

WPG

Nino Niederreiter6G 6A

0.87 xG/60 · 3 HD · 8.6% sh

Kyle Connor25G 30A

0.83 xG/60 · 2 HD · 13.0% sh

Keep going

Where to next

Back to the front page