4DFOURTH DOWN LABSWeek 1 ranks

FREE TOOL / FDL-001 MODEL

Expected
Touchdown Lab.

Enter a receiving season to compare actual touchdowns with an opportunity-based estimate.

MODEL STATUSHISTORICAL BASELINE

Not a 2026 projection

TRAINING WINDOW2014–2023

1,336 player-seasons

STUDY POPULATIONWR / TE · 40+ TGT

Inputs below threshold are flagged

SEASON INPUTS

Choose a profile or enter a player season.

QUICK START
EXPECTED TD7.27

Opportunity baseline

ACTUAL TD10

Your input

TD − xTD+2.73

Actual minus baseline

ACTUAL TD RATE7.7%

Touchdowns per target

EXPECTED TD RATE5.6%

Baseline per target

SCORING GAP+2.1 pts

Actual vs. expected rate

READ THE RESULT

+2.73 TD above baseline.

Use this as a tiebreaker, not a projection. Then consider role, quarterback, team, health, and market context.

BIGGEST MODEL DRIVERS

Receiving first downs+6.09 xTD

Targets-4.32 xTD

Receiving yards+2.31 xTD

FULL MODEL BREAKDOWN

Inputs overlap, so individual coefficients are not causal.

Intercept0.330
Targets 130 × -0.03326-4.324
Receptions 84 × 0.01193+1.002
Receiving yards 1,180 × 0.00196+2.312
Receiving air yards 1,480 × 0.00126+1.860
Receiving first downs 54 × 0.11274+6.088
RAW SUM7.2680LOWER CLIP0

HOW TO USE IT

Compare scoring
to opportunity.

Use touchdown-over-expected only as a weak historical tiebreaker after preserving opportunity and updating the current team, quarterback, health, and market context.

Read the study →

WHAT THE MODEL IS

ridge-regularized linear expected-touchdown model

Published run
2026-08-30-touchdown-regression-v1
Test season
2024
Ridge penalty
5.0
Frozen validations
3 / 3
Parameter SHA
ebd6cd8d2895…
Open model parameters ↗Open tool contract ↗

LIMITS

What this tool
does not do.

  1. This is the published 2024 walk-forward baseline trained on 2014–2023 seasons, not a 2026 player projection.
  2. Inputs below 40 targets are outside the study population.
  3. The five opportunity features are correlated; individual coefficients are not causal effects and should not be interpreted in isolation.
  4. The model omits route-level, red-zone, quarterback, team-environment, health, and betting-market information.
  5. Next-season validation conditions on players returning to at least 40 targets, creating survivor bias.
  6. Expected touchdowns were modestly better than raw touchdowns as a population baseline; both forecasts still missed by more than two touchdowns on average.