Backcheck
Pick club
Motion-blurred skater in a Montreal Canadiens sweater
← Tue, Mar 17 · the slate
Breakdown · BOS at MTL

Canadiens edge the Bruins in overtime

Final / OTTue, Mar 17
BOSBoston Bruins2MTLMontreal Canadiens3
The verdict · earned

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

BOS 2 · MTL 3
◆ By the ModelJul 12, 7:34 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

Montreal's command of this game was undeniable: 60% of expected goals (5.33–3.57), 11 high-danger chances to Boston's 5, 52% of shot attempts. They deserved the win. Cole Caufield's tip-in at 04:38 of overtime merely formalized what play itself had already determined.

But the path there revealed how thin the margin was. J. Swayman's 28 saves, at a 0.903 save percentage, outperformed his model by 2.33 goals—almost precisely the buffer Boston needed to survive Montreal's relentless pressure. Montreal, for their part, underperformed their own expected goals by 2.33 goals, squandering early premium chances.

The efficiency patterns cut both ways. Montreal was lethal on the rush: 3 goals on 31 chances, compared to Boston's 2 on 23. The Bruins, meanwhile, went 0/5 on high-danger looks, a variance that won't repeat. J. Dobes stopped everything Montreal's opposition created, posting a 0.929 save percentage—1.57 goals above expected.

Neither team converted its rebound chances. Montreal crashed the net 5 times without result; Boston did so 7 times, also empty. Overtime arrived because both teams' supplementary scoring dried up.

The breakdown in twelve frames

Swipe it

Every number is from this page
Final · OT · Mar 17
BOS
2
MTL
3

Canadiens edge the Bruins in overtime

Chances 3.6 – 5.3Did they deserve it? →
Did they deserve it?

The Canadiens earned this one.

Expected goals · chance value
BOS
3.57
MTL
5.33
40% of the chances60%

The board read BOS 2, MTL 3. The chances read BOS 3.6, MTL 5.3.

Our xG model · NHL play-by-play · all situations
Luck check
MTL
−2.3
goals above expected
MTL5.33 expected · 3 scored
Expected
Scored
BOS3.57 expected · 2 scored
Expected
Scored

The Bruins left 1.6 goals on the table against what their chances were worth.

PDO = sh% + sv% · drifts to 1.000 over a season
Every goal, in order
  1. P1 02:22BOSP. ZachaPP1–0
  2. P1 10:31MTLN. Suzuki1–1
  3. P2 05:41BOSP. Zacha2–1
  4. P2 13:15MTLJ. Anderson2–2
  5. OT 04:38MTLC. Caufield2–3
NHL play-by-play · chance value from our xG model
Where the shots came from
BOS
40 shots
2
Final
99 shots
MTL
59 shots
3
BOS attackMTL attack
BOS MTL Goal
40
shots · 2 in
59
shots · 3 in
Every unblocked shot · press play to replay it
Chances by danger
BOSMTL
0 / 5
1.45 xG
High danger
1 / 11
2.83 xG
1 / 13
1.47 xG
Medium
2 / 18
1.88 xG
1 / 37
0.66 xG
Low
0 / 47
0.62 xG

The Bruins went 0 for 5 from the slot.

Danger tiers by our xG model · high ≥ 20% chance
In the net
A
J. Swayman
+2.3
BOS · 28/31
A
J. Dobes
+1.6
MTL · 26/28
The numbers, checked
BACKCHECK

Canadiens edge the Bruins in overtime

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 13–13
  1. 02:22BOSP. Zachapower play(D. Pastrnak, C. McAvoy)1–0
  2. 10:31MTLN. Suzuki(J. Slafkovský, C. Caufield)1–1
2ndshots 8–7
  1. 05:41BOSP. Zacha(V. Arvidsson, C. Mittelstadt)2–1
  2. 13:15MTLJ. Anderson(L. Hutson, B. Gallagher)2–2
3rdshots 6–7no goals
    OTshots 1–4
    1. 04:38MTLC. Caufield(N. Suzuki, L. Hutson)2–3

    score reads BOS–MTL

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

    The numbers

    XGBoost xG · NHL play-by-play
    5.33
    MTL chances
    Goals their shots were worth
    −2.3
    Finishing
    Goals below what those chances were worth
    1.003
    MTL puck luck
    About 1.000 — a normal night for bounces
    58.0%
    Shot attempts
    Over half — they had the puck more
    Split by club

    Who controlled the game

    3.57Expected goals5.33
    MTL 60% of the chance quality
    28Shots on goal31
    5High-danger chances11
    55All attempts (Corsi)76
    Adjusted for score: BOS 41% · MTL 59%
    Faceoffs · MTL won48%off54%neu58%def
    Source · NHL play-by-play · XGBoost xG
    How the game was won

    The danger ladder

    shotsgoalsexpected
    High dangerslot & crease
    BOS0 / 5 · 1.45 xG
    MTL1 / 11 · 2.83 xG
    Medium dangermid-range
    BOS1 / 13 · 1.47 xG
    MTL2 / 18 · 1.88 xG
    Low dangerperimeter & point
    BOS1 / 37 · 0.66 xG
    MTL0 / 47 · 0.62 xG

    MTL went 1-for-11 from high danger on 2.83 expected goals — 1.8 left on the table.

    Source · Backcheck xG model · NHL play-by-play
    The luck layer

    Finishing vs expected

    expectedactual
    BOS
    2 G · 3.57 xG · -1.6
    MTL
    3 G · 5.33 xG · -2.3
    0123456

    BOS finished -1.6 against expected, MTL -2.3.

    Source · Backcheck xG model
    Shot types · rush and rebound chancesopen +
    What they shot — and what went in

    Shot diet

    goalsshots
    BOS
    SNAP0/32
    TIP IN1/2
    BACKHAND1/4
    SLAP0/1
    DEFLECTED0/0
    WRIST0/0
    POKE0/1
    BAT0/0
    OTHER0/15
    MTL
    SNAP0/39
    TIP IN2/9
    BACKHAND1/5
    SLAP0/1
    DEFLECTED0/2
    WRIST0/2
    POKE0/0
    BAT0/1
    OTHER0/17
    BOS
    MTL
    Off the rush
    2 G on 23
    1.66 xG
    3 G on 31
    3.11 xG
    Off rebounds
    0 G on 7
    1.23 xG
    0 G on 5
    0.68 xG

    Snap shots carried the volume: BOS went 0-for-32, MTL 0-for-39. MTL 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. Swayman
    BOS · 28/31 · .903
    +2.3
    saved above expected
    A
    the night
    By dangerG/attxGsaved
    High danger1/112.8+1.8
    Medium2/181.9-0.1
    Low0/470.6+0.6

    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

    J. Dobes
    MTL · 26/28 · .929
    +1.6
    saved above expected
    A
    the night
    By dangerG/attxGsaved
    High danger0/51.4+1.4
    Medium1/131.5+0.5
    Low1/370.7-0.3

    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
    BOS
    40 shots
    2
    Final
    99 shots
    MTL
    59 shots
    3
    BOS attackMTL attack
    BOS MTL Goal

    Each club shoots toward its own end — BOS left, MTL 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
    N. Suzuki
    #14 · C · MTL
    1 G · 1 A · 3 SOG · 24:18 on ice · +2
    L. Hutson
    #48 · D · MTL
    0 G · 2 A · 1 SOG · 21:41 on ice · +1
    C. Caufield
    #13 · R · MTL
    1 G · 1 A · 4 SOG · 19:58 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, 8:10 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 a 2.5 to 2.7 goal game, with Montreal at 53% win probability—which is to say Boston and Montreal are essentially interchangeable here. This is pick'em territory.

    The underlying numbers bear that out. Boston leads in even-strength Corsi at 49.0%, which Montreal matches exactly; Montreal edges expected goals share at 48.0% to Boston's 47.0%. Neither team has built a possession edge meaningful enough to carry the weight of this matchup.

    What matters more is what both teams have built in the periphery. Boston's PDO sits at 1.023, Montreal's at 1.018—both are running hot on luck. When PDO normalizes, both teams will regress. The question is how much and how fast, and whether that regression happens tonight.

    J. Korpisalo figures into Montreal's equation on the back of a back-to-back, which may necessitate a backup start or simply a tired starter. That's a variable Boston should exploit if the opportunity arrives.

    On offense, Viktor Arvidsson has been Boston's primary weapon: 1.04 expected goals per 60 minutes, 18 goals and 24 assists with two high-danger chances and a 13.0% shooting rate that suggests he's been executing at the net. Tanner Jeannot pairs with him at 0.75 xG/60, with six goals against an 8.3% shooting percentage—another indicator he's been efficient.

    Montreal counters with Cole Caufield, who is running at 0.97 xG/60 with 33 goals and 16 assists. That 20.0% shooting rate is unsustainable; when it normalizes downward, Caufield's goal total will follow. Oliver Kapanen at 0.83 xG/60 with four high-danger chances gives Montreal secondary punch at 17.8% shooting, though again, that rate will regress.

    The matchups offer little separation. Both teams have managed 0% of their goals from high-danger situations and 0% from rebounds—an unusual statistical vacuum that will eventually resolve. Boston's defensive weak link is Elias Lindholm; Montreal's is Mike Matheson. Neither hole is so large as to swing a game this close.

    The model is right. This is a flip. Boston's possession advantage is negligible, and Montreal's shooting efficiency will normalize. The team that capitalizes on the first margin—J. Korpisalo's potential rust, a spike in high-danger finishing, or a turnover by Lindholm or Matheson—likely wins.

    What the model said beforehand

    The model's lean

    MTL 53%
    53%
    MTL
    Model favorite
    47%
    53%
    BOS50MTL

    MTL by 6 points of win probability — a modest lean. Projected score BOS 2.5–2.7 MTL; 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
    BOS← edge
    edge →MTL
    47.0%48.0%
    49.0%49.0%
    2.392.41
    2.672.62
    2.222.24
    1.821.96
    1.0231.018

    MTL holds 5 of 6 process categories — and the luck row (1.023 vs 1.018) says BOS has been getting the bounces, which tends not to last.

    Source · NHL stats API + our xG · 5v5
    Form · Last 10
    BOS
    5-3-2
    -2 GD · 1d rest
    MTL
    5-3-2
    +5 GD · 2d rest
    1.023
    BOS PDO
    Luck gauge · drifts to 1.000
    1.018
    MTL PDO
    Luck gauge · drifts to 1.000
    What decides it

    Keys to the game

    Regression watch
    • The Canadiens' PDO is 1.018 — running hot, expect some regression.
    • The Bruins' PDO is 1.023 — running hot, expect some regression.
    Things to watch
    • J. Korpisalo is on a back-to-back — watch for a backup start or a tired starter.
    • The Canadiens' PDO is 1.018 — running hot, expect some regression.
    Last game's lineup · confirmed at warm-up

    Lineups

    NHL box score
    BOS
    Expected in goal
    J. Korpisalo
    back-to-back.882 last start
    Backup Jeremy Swayman · +28.8 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.

    MTL
    Expected in goal
    J. Fowler
    2 days rest.857 last start
    Backup Jakub Dobes · +17.3 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
    BOS
    Viktor Arvidsson18G 24A
    1.04 xG/60 · 2 HD · 13.0% sh
    Tanner Jeannot6G 14A
    0.75 xG/60 · 2 HD · 8.3% sh
    MTL
    Cole Caufield33G 16A
    0.97 xG/60 · 1 HD · 20.0% sh
    Oliver Kapanen19G 12A
    0.83 xG/60 · 4 HD · 17.8% sh
    Keep going

    Where to next

    Back to the front page