Motion-blurred skater in a Nashville Predators sweater

Breakdown · NSH at WPG

Predators steal one from the Jets against the run of play

Final / OTTue, Mar 17

NSHNashville Predators4 WPGWinnipeg Jets3

The verdict · stolen

The Predators stole one. They lost the expected-goals battle 2.55–5.07 and won anyway.

NSH 4 · WPG 3

◆ By the ModelJul 12, 7:36 AMxG: 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

Nashville won a game it didn't deserve to win. Winnipeg commanded 66% of expected goals, but lost in a shootout anyway.

J. Saros stole this one. The Predators goaltender made 36 of 39 saves—a 0.923 save percentage—and outperformed his expected save rate by 2.07 goals, the sort of performance that turns an xG blowout into a theft.

The Jets generated the chances. Winnipeg owned 63% of shot attempts (39 on goal to Nashville's 23) and a 9–2 edge in high-danger chances. Their power play scored twice on 18 shots, generating 1.41 expected goals. They crashed the net relentlessly, creating 11 rebound opportunities. Yet Winnipeg underperformed its xG by 2.07 goals, wasting the quality they'd earned.

Nashville's efficiency did the damage. The Predators converted 3 goals on 29 rush chances. C. Hellebuyck (20 saves, 0.870 SV%) played reasonably, but the barrage of expected goals should have overwhelmed him.

The breakdown in twelve frames

Swipe it

Every number is from this page

Final · SO · Mar 17

NSH

WPG

Predators steal one from the Jets against the run of play

Chances 2.5 – 5.1Did they deserve it? →

Did they deserve it?

The Jets deserved better.

Expected goals · chance value

NSH

2.55

WPG

5.07

34% of the chances67%

The board read NSH 4, WPG 3. The chances read NSH 2.5, WPG 5.1.

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

Luck check

NSH

+1.4

goals above expected

NSH2.55 expected · 4 scored

Expected

Scored

WPG5.07 expected · 3 scored

Expected

Scored

The Jets left 2.1 goals on the table against what their chances were worth.

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

Every goal, in order

P1 13:02NSHE. HaulaPP1–0
P1 19:20WPGJ. Morrissey1–1
P2 05:09WPGG. VilardiPP1–2
P2 10:48NSHF. Forsberg2–2
P3 14:01NSHM. Wood3–2
P3 18:59WPGJ. ToewsPP3–3
SO 00:00NSHR. O'ReillyPP3–3

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

Where the shots came from

NSH

39 shots

Final

99 shots

WPG

60 shots

NSH WPG GoalBigger dot · more dangerous look

shots · 4 in

shots · 3 in

Every unblocked shot · press play to replay it

Chances by danger

NSHWPG

0 / 2

0.40 xG

High danger

1 / 9

2.03 xG

3 / 13

1.49 xG

Medium

2 / 19

2.08 xG

0 / 36

0.67 xG

Low

0 / 48

0.97 xG

High-danger looks: NSH 0 of 2, WPG 1 of 9.

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

In the net

J. Saros

+2.1

NSH · 36/39

C. Hellebuyck

−0.5

WPG · 20/23

The numbers, checked

BACKCHECK

Predators steal one from the Jets against the run of play

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 7–14

13:02NSHE. Haulapower play(R. Josi, L. Evangelista)1–0
19:20WPGJ. Morrissey(G. Vilardi, K. Connor)1–1

2ndshots 8–12

05:09WPGG. Vilardipower play(C. Perfetti, K. Connor)1–2
10:48NSHF. Forsberg(J. Marchessault, R. Ufko)2–2

3rdshots 6–9

14:01NSHM. Wood(J. Marchessault, F. Forsberg)3–2
18:59WPGJ. Toewspower play(M. Scheifele, K. Connor)3–3

OTshots 2–4no goals

00:00NSHR. O'Reillypower play3–3

score reads NSH–WPG

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

Process vs result

The numbers

XGBoost xG · NHL play-by-play

2.55

NSH chances

Goals their shots were worth

+1.4

Finishing

Goals above what those chances were worth

1.019

NSH puck luck

About 1.000 — a normal night for bounces

40.2%

Shot attempts

Under half — they were outshot

Split by club

Who controlled the game

2.55Expected goals5.07

WPG 67% of the chance quality

23Shots on goal39

2High-danger chances9

51All attempts (Corsi)76

Adjusted for score: NSH 40% · WPG 60%

Faceoffs · WPG won57%off63%neu44%def

Source · NHL play-by-play · XGBoost xG

How the game was won

The danger ladder

shotsgoalsexpected

High dangerslot & crease

NSH0 / 2 · 0.40 xG

WPG1 / 9 · 2.03 xG

Medium dangermid-range

NSH3 / 13 · 1.49 xG

WPG2 / 19 · 2.08 xG

Low dangerperimeter & point

NSH0 / 36 · 0.67 xG

WPG0 / 48 · 0.97 xG

NSH went 3-for-13 from medium danger on 1.49 expected goals — 1.5 above expected.

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

The luck layer

Finishing vs expected

expectedactual

NSH

4 G · 2.55 xG · +1.4

WPG

3 G · 5.07 xG · -2.1

0123456

NSH finished +1.4 against expected, WPG -2.1.

Source · Backcheck xG model

Shot types · rush and rebound chancesopen +

What they shot — and what went in

Shot diet

goalsshots

NSH

WRIST0/15

SLAP1/9

SNAP1/6

TIP IN1/7

BACKHAND0/0

OTHER0/14

WPG

WRIST2/31

SLAP0/7

SNAP1/7

TIP IN0/6

BACKHAND0/6

OTHER0/19

NSH

WPG

Off the rush

3 G on 29

2.28 xG

1 G on 36

2.56 xG

Off rebounds

0 G on 1

0.10 xG

1 G on 11

1.85 xG

Wrist shots carried the volume: NSH went 0-for-15, WPG 2-for-31. NSH 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

J. Saros

NSH · 36/39 · .923

+2.1

saved above expected

the night

By dangerG/attxGsaved

High danger1/92.0+1.0

Medium2/192.1+0.1

Low0/481.0+1.0

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

C. Hellebuyck

WPG · 20/23 · .870

-0.5

saved above expected

the night

By dangerG/attxGsaved

High danger0/20.4+0.4

Medium3/131.5-1.5

Low0/360.7+0.7

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

99 shots · press play to watch the game back

Where the shots came from

NHL play-by-play coordinates

NSH

39 shots

Final

99 shots

WPG

60 shots

NSH WPG GoalBigger dot · more dangerous look

Each club shoots toward its own end — NSH 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

K. Connor

#81 · L · WPG

0 G · 3 A · 7 SOG · 25:17 on ice · +2

G. Vilardi

#13 · C · WPG

1 G · 1 A · 6 SOG · 21:56 on ice · +2

J. Marchessault

#81 · R · NSH

0 G · 2 A · 3 SOG · 18:12 on ice · +2

Ranked from the box score — points first · Backcheck

What the model said beforehand

Before the game

Written Tue, Mar 17

Open the pre-game read

Written from the numbers

The read

Edited for clarity

◆ By the ModelJul 12, 7:34 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

The model projects 2.5 to 2.6 expected goals per team, leaving Winnipeg at 51% win probability. This is as close to a pick'em as the sport gets.

Winnipeg has momentum: 6-2-2 over their last 10 games. But the underlying 5v5 picture is nearly symmetrical. Nashville posts 49.0% expected goal share and 50.0% Corsi; Winnipeg sits at 48.0% and 49.0%. Their PDO figures—0.992 and 0.998—are indistinguishable noise.

The swing factor could be goaltending. J. Annunen is on a back-to-back, which usually means either a backup start or a starter playing on fumes.

Nashville's top scorers are Zachary L'Heureux and Filip Forsberg. L'Heureux generates 0.85 expected goals per 60 with 4 goals on 16.0% shooting—a rate destined to regress—but has 1 high-danger goal backing the efficiency. Forsberg runs 0.80 xG/60, has 23 goals at 13.6% shooting, and 4 high-danger goals, suggesting he's sustaining his run through both volume and shot quality.

Winnipeg's Nino Niederreiter posts 0.87 xG/60 with 6 goals and 6 assists despite an 8.6% shooting rate and 3 high-danger markers—a profile that says the goals should keep coming. Kyle Connor, the team's leading scorer at 25 goals and 30 assists, plays at 0.83 xG/60 on 13.0% shooting with only 2 high-danger goals, a red flag that his current pace is unsustainable.

Both teams are posting 0% high-danger goal rates and 0% rebound goal rates, suggesting either measurement gaps or teams finding offense through play outside the danger zone. Nashville's Jonathan Marchessault represents a defensive liability; Winnipeg's Colin Miller is flagged as vulnerable on the back end.

Every number points the same direction: this is a coin flip. The winner will likely be whichever team avoids mistakes late and solves whatever goaltending situation Nashville's back-to-back creates.

What the model said beforehand

The model's lean

WPG 51%

51%

WPG

Model favorite

49%

51%

NSH50WPG

WPG by 2 points of win probability — effectively a coin flip. Projected score NSH 2.5–2.6 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

NSH← edge

edge →WPG

49.0%48.0%

50.0%49.0%

2.482.34

2.582.55

1.841.90

2.212.10

0.9920.998

The season numbers split 3–3 — no clear process edge — and the luck row (0.992 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

NSH

3-5-2

-3 GD · 1d rest

WPG

6-2-2

+1 GD · 2d rest

0.992

NSH 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

J. Annunen is on a back-to-back — watch for a backup start or a tired starter.
The Jets are the hotter team by points pace (6-2-2 in their last 10).

Last game's lineup · confirmed at warm-up

Lineups

NHL box score

NSH

Expected in goal

J. Annunen

back-to-back.931 last start

Backup Juuse Saros · -9.3 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.

WPG

Expected in goal

E. Comrie

2 days rest.935 last start

Backup Connor Hellebuyck · +5.5 GSAx this season

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

NSH

Zachary L'Heureux4G 0A

0.85 xG/60 · 1 HD · 16.0% sh

Filip Forsberg23G 17A

0.80 xG/60 · 4 HD · 13.6% 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