Motion-blurred skater in a New York Islanders sweater
Breakdown · NYI at CBJ

Islanders edge the Blue Jackets in overtime

The verdict · earned

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

NYI 4 · CBJ 3
◆ By the ModelJul 12, 4:50 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

High-danger chances said the Blue Jackets should have won. They created two; the Islanders created one. The Islanders won anyway, 4-3 in overtime, because Ilya Sorokin played brilliantly and Joonas Greaves did not. Sorokin stopped 27 of 30 shots for a 0.900 save percentage. Greaves surrendered 23 of 27 for a 0.852 save percentage, 0.88 goals worse than his underlying volume predicted.

Simon Holmstrom settled it at 01:47 of overtime with a wrist shot from the doorstep. The game had already been decided.

Columbus commanded the underlying matrix. They out-attempted New York 30-27 and expected goals ran 2.82–3.12, a slight edge to the Islanders. The Blue Jackets were lethal on the rush, scoring two goals on 25 chances—a rate that should carry teams to victory. They attacked the net, generating seven rebound opportunities. None converted. The Islanders created six rebound chances and converted one, a trifle until you note this: the Islanders ran 0.88 goals above their expected total, and Greaves ran 0.88 below his. Same variance, opposite ends.

Z. Werenski led the Columbus assault with two assists over 28:02. M. Barzal answered for the Islanders with two assists in 20:52. S. Mayfield, the third star, produced a goal and an assist in just 14:19—production that underscores New York's clinical finish.

The underlying numbers promised a game too close to call. Sorokin made it look settled.

The breakdown in twelve frames

Swipe it

Every number is from this page
Final · OT · Feb 28
NYI
4
CBJ
3

Islanders edge the Blue Jackets in overtime

Chances 3.1 – 2.8Did they deserve it? →
Did they deserve it?

Dead even on chances. The Islanders took it anyway.

Expected goals · chance value
NYI
3.12
CBJ
2.82
53% of the chances47%

The board read NYI 4, CBJ 3. The chances read NYI 3.1, CBJ 2.8.

Our xG model · NHL play-by-play · all situations
Luck check
NYI
+0.9
goals above expected
NYI3.12 expected · 4 scored
Expected
Scored
CBJ2.82 expected · 3 scored
Expected
Scored

Both sides finished close to what their chances were worth. This one was earned on the ice.

PDO = sh% + sv% · drifts to 1.000 over a season
Every goal, in order
  1. P1 02:30CBJI. Lundeström0–1
  2. P2 03:58CBJM. Marchment0–2
  3. P2 11:37NYIA. Lee1–2
  4. P2 11:59NYIJ. Pageau2–2
  5. P2 17:10NYIS. Mayfield3–2
  6. P2 18:58CBJA. Fantilli3–3
  7. OT 01:47NYIS. Holmstrom4–3
NHL play-by-play · chance value from our xG model
Where the shots came from
NYI
44 shots
4
Final
88 shots
CBJ
44 shots
3
NYI attackCBJ attack
NYI CBJ Goal
44
shots · 4 in
44
shots · 3 in
Every unblocked shot · press play to replay it
Chances by danger
NYICBJ
1 / 2
0.56 xG
High danger
0 / 1
0.23 xG
2 / 15
1.88 xG
Medium
3 / 16
1.84 xG
1 / 49
0.69 xG
Low
0 / 48
0.74 xG

High-danger looks: NYI 1 of 2, CBJ 0 of 1.

Danger tiers by our xG model · high ≥ 20% chance
In the net
C
I. Sorokin
−0.2
NYI · 27/30
D-
J. Greaves
−0.9
CBJ · 23/27
The numbers, checked
BACKCHECK

Islanders edge the Blue Jackets 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 5–11
  1. 02:30CBJI. Lundeström(D. Fabbro, M. Wood)0–1
2ndshots 11–16
  1. 03:58CBJM. Marchment(C. Coyle, Z. Werenski)0–2
  2. 11:37NYIA. Lee(S. Mayfield, J. Pageau)1–2
  3. 11:59NYIJ. Pageau2–2
  4. 17:10NYIS. Mayfield(M. Barzal)3–2
  5. 18:58CBJA. Fantilli(Z. Werenski)3–3
3rdshots 10–3no goals
    OTshots 1–0
    1. 01:47NYIS. Holmstrom(T. DeAngelo, M. Barzal)4–3

    score reads NYI–CBJ

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

    The numbers

    XGBoost xG · NHL play-by-play
    3.12
    NYI chances
    Goals their shots were worth
    +0.9
    Finishing
    Goals above what those chances were worth
    1.014
    NYI puck luck
    About 1.000 — a normal night for bounces
    50.4%
    Shot attempts
    Over half — they had the puck more
    Split by club

    Who controlled the game

    3.12Expected goals2.82
    NYI 53% of the chance quality
    27Shots on goal30
    2High-danger chances1
    66All attempts (Corsi)65
    Adjusted for score: NYI 53% · CBJ 47%
    Faceoffs · CBJ won57%off45%neu32%def
    Source · NHL play-by-play · XGBoost xG
    How the game was won

    The danger ladder

    shotsgoalsexpected
    High dangerslot & crease
    NYI1 / 2 · 0.56 xG
    CBJ0 / 1 · 0.23 xG
    Medium dangermid-range
    NYI2 / 15 · 1.88 xG
    CBJ3 / 16 · 1.84 xG
    Low dangerperimeter & point
    NYI1 / 49 · 0.69 xG
    CBJ0 / 48 · 0.74 xG

    CBJ went 3-for-16 from medium danger on 1.84 expected goals — 1.2 above expected.

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

    Finishing vs expected

    expectedactual
    NYI
    4 G · 3.12 xG · +0.9
    CBJ
    3 G · 2.82 xG · +0.2
    012345

    NYI finished +0.9 against expected, CBJ +0.2.

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

    Shot diet

    goalsshots
    NYI
    WRIST2/20
    SNAP1/11
    TIP IN1/5
    BACKHAND0/2
    SLAP0/4
    DEFLECTED0/2
    OTHER0/22
    CBJ
    WRIST1/23
    SNAP0/11
    TIP IN2/5
    BACKHAND0/4
    SLAP0/0
    DEFLECTED0/1
    OTHER0/21
    NYI
    CBJ
    Off the rush
    1 G on 20
    1.72 xG
    2 G on 25
    1.60 xG
    Off rebounds
    1 G on 6
    0.97 xG
    0 G on 7
    0.84 xG

    Wrist shots carried the volume: NYI went 2-for-20, CBJ 1-for-23. CBJ scored 2 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
    I. Sorokin
    NYI · 27/30 · .900
    -0.2
    saved above expected
    C
    the night
    By dangerG/attxGsaved
    High danger0/10.2+0.2
    Medium3/161.8-1.2
    Low0/480.7+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

    J. Greaves
    CBJ · 23/27 · .852
    -0.9
    saved above expected
    D-
    the night
    By dangerG/attxGsaved
    High danger1/20.6-0.4
    Medium2/151.9-0.1
    Low1/490.7-0.3

    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

    88 shots · press play to watch the game back

    Where the shots came from

    NHL play-by-play coordinates
    NYI
    44 shots
    4
    Final
    88 shots
    CBJ
    44 shots
    3
    NYI attackCBJ attack
    NYI CBJ Goal

    Each club shoots toward its own end — NYI left, CBJ 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
    Z. Werenski
    #8 · D · CBJ
    0 G · 2 A · 5 SOG · 28:02 on ice · +1
    M. Barzal
    #13 · C · NYI
    0 G · 2 A · 1 SOG · 20:52 on ice
    S. Mayfield
    #24 · D · NYI
    1 G · 1 A · 4 SOG · 14:19 on ice · +2
    Ranked from the box score — points first · Backcheck
    What the model said beforehand

    Before the game

    Written Sat, Feb 28
    Open the pre-game read
    Written from the numbers

    The read

    Edited for clarity
    ◆ By the ModelJul 12, 4:48 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

    Columbus owns the underlying play here. The model projects a 2.5–2.8 Blue Jackets victory with Columbus holding 56% win probability—a lean backed by the season's 5v5 numbers. Columbus owns 52.0% expected goals and 51.0% Corsi at 5v5, against New York's 48.0% xG and 49.0% Corsi. These aren't blowout margins, but they're consistent across both volume and quality metrics.

    Form favors the road team. Columbus is 8-2-0 in their last 10 games, translating to a points pace well above league average. New York is playing at a lower clip—one reason the model projects them as a secondary outcome.

    Both starters face back-to-back pressure. E. Merzlikins handles the bulk of Columbus's workload, while I. Sorokin anchors New York. Either could see a backup pressed into duty depending on coaching decisions and recovery needs.

    The player edge tilts toward Columbus's depth. Bo Horvat drives the Islanders' offense with 18 goals, though he posts just a 12.8% shooting rate on 0.87 xG/60—suggesting some luck in conversion. Anders Lee, New York's power-play driver, carries 1.20 xG/60 with 9 goals and 2 high-danger chances, but his 6.4% shooting is below typical benchmarks. Boone Jenner leads Columbus with 0.98 xG/60 and 21 assists against 11 goals, implying quality creation rate-limited by finishing. Mathieu Olivier adds 0.89 xG/60 with a 13.3% shooting rate—a secondary weapon at full efficiency.

    Columbus's possession edge sits atop a small PDO advantage. Columbus's 1.003 PDO versus New York's 0.993 suggests marginal puck-luck benefits, but the underlying volume advantage is the real story. New York's defensive weak link, Alexander Romanov, faces another night in a compressed system. Columbus counters with Conor Garland, a forward who'll anchor secondary matchups.

    Players to Watch

    • Anders Lee (NYI) — 1.20 xG/60, 9G–20A, 2 HD goals, 6.4% shooting
    • Bo Horvat (NYI) — 0.87 xG/60, 18G–10A, 3 HD goals, 12.8% shooting
    • Boone Jenner (CBJ) — 0.98 xG/60, 11G–21A, 2 HD goals, 9.6% shooting
    • Mathieu Olivier (CBJ) — 0.89 xG/60, 12G–9A, 1 HD goal, 13.3% shooting
    What the model said beforehand

    The model's lean

    CBJ 56%
    56%
    CBJ
    Model favorite
    44%
    56%
    NYI50CBJ

    CBJ by 12 points of win probability — a modest lean. Projected score NYI 2.5–2.8 CBJ; 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
    NYI← edge
    edge →CBJ
    48.0%52.0%
    49.0%51.0%
    2.482.63
    2.692.43
    1.782.12
    1.941.98
    0.9931.003

    CBJ holds 5 of 6 process categories — and the luck row (0.993 vs 1.003) says CBJ has been getting the bounces, which tends not to last.

    Source · NHL stats API + our xG · 5v5
    Form · Last 10
    NYI
    6-4-0
    +0 GD · 1d rest
    CBJ
    8-2-0
    +13 GD · 1d rest
    0.993
    NYI PDO
    Luck gauge · drifts to 1.000
    1.003
    CBJ PDO
    Luck gauge · drifts to 1.000
    What decides it

    Keys to the game

    Where the edges live
    • The Blue Jackets own the underlying play — 52.0% 5v5 xG vs 48.0%.
    Things to watch
    • The Blue Jackets own the underlying play — 52.0% 5v5 xG vs 48.0%.
    • E. Merzlikins is on a back-to-back — watch for a backup start or a tired starter.
    • I. Sorokin is on a back-to-back — watch for a backup start or a tired starter.
    • The Blue Jackets are the hotter team by points pace (8-2-0 in their last 10).
    Last game's lineup · confirmed at warm-up

    Lineups

    NHL box score
    NYI
    Expected in goal
    I. Sorokin
    back-to-back.880 last start
    Backup Ilya Sorokin · +25.3 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.

    CBJ
    Expected in goal
    E. Merzlikins
    back-to-back.864 last start
    Backup Jet Greaves · +16.5 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
    NYI
    Anders Lee9G 20A
    1.20 xG/60 · 2 HD · 6.4% sh
    Bo Horvat18G 10A
    0.87 xG/60 · 3 HD · 12.8% sh
    CBJ
    Boone Jenner11G 21A
    0.98 xG/60 · 2 HD · 9.6% sh
    Mathieu Olivier12G 9A
    0.89 xG/60 · 1 HD · 13.3% sh
    Keep going

    Where to next