xJawn NHL expected goals

← Games

SEA @ BOS

2026-01-15 · final 2–4 · what happened, next to what the engine said before puck drop

Final (SEA–BOS)
2–4
Actual xG (SEA–BOS)
3.49–2.16
Predicted xG
2.24–3.01
The call
BOS 63.3%

What happened

SEA attacks the left net, BOS the right — every unblocked attempt the game produced: × goals, on net, missed (hover a marker for the shooter and its xG). To compare against the pregame call, switch the Surface to the engine's predicted-xG map — the shots land on top of where the engine expected the game to be played.

SEABOS
2Goals3
3.49Expected goals (xG)2.16
1.605v5 xG1.39
1.89Power-play xG0.68
28Shots on goal23
62Shot attempts46

Counts come from the shot table behind the maps: empty-net attempts and the shootout are excluded, so the goals row can trail the official final by an empty-netter or the shootout's deciding goal.

Goals

TeamScorerPeriodStrengthxG
SEAChandler Stephenson 1 PP 0.10
BOSMarat Khusnutdinov 1 5v5 0.31
BOSViktor Arvidsson 1 5v5 0.07
SEAEeli Tolvanen 2 PP 0.21
BOSMark Kastelic 2 PK 0.08

The prediction, scored

Before puck drop the engine made BOS a 63.3% favorite, expecting a 2.24–3.01 game — BOS won 2–4, so the call landed. Every number in this section was issued before the game and is never re-graded.

pred. xGactual xG pred. 5v5actual 5v5 pred. STactual PP
SEA 2.243.49 1.521.60 0.611.89
BOS 3.012.16 2.101.39 0.730.68

Predicted 5v5 / special-teams portions come from the map's strength splits (one shared scale per team pins the all-strengths total to its expected goals), so they don't sum exactly — the remainder is 4v4, 3v3, and other mixed states. The actual PP column is power-play xG only, the same bucket the map's special-teams view draws.

The pregame score grid

The likeliest finals the engine saw before the game, with what actually happened marked — SEA · BOS.

Likeliest finals (SEA–BOS)probability
2–3 6.0%
2–2 6.0% tied after regulation — OT/SO decides
1–3 5.4%
1–2 5.3%
2–4 4.5% what happened
10.7%4.9%023.9%14.8%126.7%22.3%219.9%22.4%311.1%16.9%45.0%10.2%51.9%5.1%60.6%2.2%70.2%1.2%8+

Scoreline odds treat the two teams' totals as independent — the engine's known simplification (it slightly under-counts regulation ties; the correlation term is registered v1.1 work). The OT/SO layer is a separate fitted model and is already inside the headline win probability.

The pregame read

The engine made BOS a 63.3% favorite — BOS controls 57.4% of the predicted xG. Of SEA's 2.24 expected goals, 1.52 should come at 5v5 and 0.61 on the power play; BOS projects 2.10 at 5v5 and 0.73 on the power play. The logistic challenger put the home side at 67.9%, Elo at 65.2%.

Tale of the tape

How each team fares on its own, season to date: per-game xG rates with league rank (of 32). Rank 1 is best on every row — orange ranks sit in the top third of the league, gray in the bottom third.

SEABOS
2.50 (31st) Offense
xG for / game
2.70 (23rd)
2.93 (17th) Defense
xG against / game
3.12 (29th)
0.61 (28th) Power play
PP xG / game
0.68 (20th)
0.66 (15th) Penalty kill
PP xG conceded / game
0.88 (32nd)

Season-to-date form as of the site's latest build, shown for context — the ratings the engine actually used were its own as-of-game-day state. Replay this matchup in the lab →