Projected shots on goal for every skater on the slate, with the probability of going over or under 1.5, 2.5 and 3.5. An XGBoost regression projects the mean from his recent shot volume and ice time and the opponent's shots allowed; a count distribution turns it into the chance at each line.
The over/under lines on this page are the model's own ladder, not a sportsbook's — compare the projection to the number your book is hanging. Graded picks are settled against the box score after the night's last game is final, on the performance page.
Every skater on the slate, every line on the ladder and the model's picks, updated three times a day.See plans, or read how the projections are built below.
See plans →Shots on goal follow ice time. A top-line winger on the first power-play unit gets four or five looks a night; a third-pair defenseman gets one. The model starts there: his shots per 60 minutes times his ice time over the last three games, a weighted average of his shots that leans on recent games, this season's shots per game pulled toward last season's, his recent and career ice time, and his position. It adds the opponent's shots allowed per game over their last ten.
That gives a projected mean. Shots are small whole numbers, so the over and under probability at each line comes from a count distribution around that mean (a negative binomial, its spread measured on a season the model did not train on), not a bell curve. A skater needs ten games played before he gets a projection.
Each card shows the projection, the over/under split at the line nearest to it — roughly where a book would hang its main number — and a bar for each of his last ten games, green where he cleared that line. A 3.1 projection with seven green bars is a different read from a 3.1 with bars that alternate, even when the probability is the same. Open "Every line" for the full ladder.
Ignore the lopsided rungs. A fourth-line defenseman will always show a high probability under 3.5; that is arithmetic, not an opinion. The useful signal is a projection that sits well away from the line.
Less than you would think. Over three seasons of box scores, skaters averaging three or more shots over their previous ten games went over 1.5 in 78.8% of the games their team won and 77.0% of the games it lost. At 2.5 the gap is gone: 56.5% against 56.2%.
Losing teams keep shooting. Winners averaged 29.2 shots on goal and losers 28.3, and the losing team outshot the winner in 1,748 of 3,936 games. Overtime adds minutes for both sides: shooters whose team lost in overtime or a shootout still cleared 1.5 in 79.4% of games, more often than those whose team won in regulation (77.8%). A shots prop is a bet on minutes and role, not on the final score.
The graded shots play is the over 1.5 on every skater the model gives 75% or better, with no daily cap. Each one is settled against the official box score after the night's last game is final: two or more shots wins, one or none loses. A skater who is scratched or never takes a shift is no result, not a loss.
The record covers the 2026-27 season and sits on the performance page with every other market. The current model went live in October; the games before that were replayed with it, and it was trained on earlier seasons only, so none of them was in its training data. The previous model's live record is kept beside it. Last season's version, the top two picks a day at 65% or better, finished with 54 graded picks, too few to quote a hit rate from.
The model projects a mean from the skater's shot rate times his recent ice time, his recent and season shot averages, his ice time, position and the opponent's shots allowed. A count distribution around that mean, with its spread measured on an unseen season, gives the over and under probability at 1.5, 2.5 and 3.5.
Ice time and power-play role. A player who logs 20 minutes and sits on the first power-play unit has a far higher floor than one playing 13 minutes at even strength. Opponent style matters next: teams that allow a lot of shots raise every skater's projection against them.
The graded play is the over 1.5 on every skater the model gives 75% or better, settled against the official box score after the night's games are final. Two or more shots is a win. A skater who is scratched or never takes a shift is no result. The record covers the whole 2026-27 season; games before the current model went live were replayed with it.
Only slightly. Over three NHL seasons, skaters averaging three or more shots over their last ten games went over 1.5 in 78.8% of team wins and 77.0% of losses; at 2.5 it was 56.5% and 56.2%. Losing teams still averaged 28.3 shots to the winners' 29.2.
No. The lines on this page are the model's own ladder at 1.5, 2.5 and 3.5 shots, so compare the projection with the number your book is hanging. A projection well above or below the book line is the signal, not the probability alone.
Because the ladder includes lines far from their projection. A defenseman projected for 0.8 shots will always show a very high probability under 2.5 or 3.5; that rung says little. Read the probability at the line nearest the projection instead.
Shots on goal, goalie saves, goals, assists, points and hits, plus live in-game signals. MLB, NFL and NBA included.
See plansFor information only. 21+. If gambling is a problem for you or someone you know, call 1-800-GAMBLER.