MODEL ACCOUNTABILITY · 2026/27

Model Performance

What Fantasy Hockey Intel predicted, when the forecast was recorded, and what happened afterward. Published outcomes include misses, incomplete samples and unresolved calls.

Data sourcesActual scoring and games played, plus observed deployment: NHL.com. Advanced shot-process and expected-goal inputs: MoneyPuck. Fantasy Hockey Intel forecasts, Expected P/G and discovery signals are model outputs, not statistics published by either source.

Preseason Forecasts

Fourteen archived rate predictions for 2026/27, compared with actual production as the season progresses.

14 / 14 with games
Source transparencyThese preseason predictions were supplied as an archived list. Their original publication timestamp has not been independently verified; they are not represented as earlier Forecast Ledger records. During 2026/27 Actual P/G updates with Player CURRENT. After season rollover it uses the last stored 2026/27 Forecast Ledger sample; neither is a retrospective change to the prediction.
Player / forecastForecast P/GConfidenceActual P/GGPOutside rangeAssessment
Andrei SvechnikovCareer-year level production if healthy 0.95–1.05 High 0.92 13 -0.03 10+ GP · provisional
Nico HischierSignificant positive regression 0.90–1.00 High 0.64 11 -0.26 10+ GP · provisional
Adam FantilliGenuine breakout 0.80–0.90 High 0.44 9 -0.36 Very early sample
Connor BedardElite scoring rate after return 1.10–1.20 High on rate 1.00 4 -0.10 Very early sample
Rasmus DahlinRemains elite fantasy D 0.85–0.95 High 0.63 8 -0.22 Very early sample
Leo CarlssonBreakout continues, largely priced in 0.95–1.05 High 1.18 11 +0.13 10+ GP · provisional
Beckett SenneckeYear-two progression after established NHL rookie season 0.75–0.85 Medium 0.82 11 0.00 10+ GP · provisional
Jesper BrattModerate rebound 0.90–0.98 Medium 0.91 11 0.00 10+ GP · provisional
Will SmithFurther growth, process must validate role 0.85–0.95 Medium 0.67 12 -0.18 10+ GP · provisional
Pavel DorofeyevProduction mostly survives team change 0.75–0.85 Medium 0.54 13 -0.21 10+ GP · provisional
Nick SuzukiRegression, but remains high-end 0.98–1.10 High 1.33 9 +0.23 Very early sample
Clayton KellerBelow 100-point breakout expectations 0.90–1.00 High 1.25 12 +0.25 10+ GP · provisional
Brandt ClarkeOpportunity improves faster than process 0.45–0.55 Medium 0.78 9 +0.23 Very early sample
Alex TuchMore likely solid than major fantasy riser 0.70–0.80 Medium 0.90 10 +0.10 10+ GP · provisional

Outside range is zero when observed P/G is inside the forecast interval; otherwise it is the signed distance from the nearest boundary. Confidence is the original qualitative forecast confidence, not a statistical probability. No final hit/miss labels are assigned midseason.

Methodology

Preseason rate ranges are fixed historical statements supplied in an archive; Radar discoveries and explicit role predictions are timestamped prospectively. The existing model Forecast Ledger retains immutable versions of Expected P/G, Driver, Deployment and Confidence. We do not backdate new predictions, revise recorded starting values, or classify a few early games as final evidence.