Kickers DST QB RB WR TE Methodology Accuracy Draft Kit

Go Premium

EVERY HIT. EVERY MISS. PUBLIC.

Track Record

Every model is tested the hard way: train on every season before year X, predict year X blind, repeat — a model never gets graded on a season it has seen. The numbers below are the 2025 season, scored exactly once, after every model decision was frozen and written down in advance. In-season grading starts Week 1 of 2026 and posts here as it lands, hits and misses alike. How the testing works in full: read the Methodology.

How the backtest works

Fold 120182019202020212022202320242025

Fold 220182019202020212022202320242025

Fold 320182019202020212022202320242025

Fold 420182019202020212022202320242025

Fold 520182019202020212022202320242025

Final test20182019202020212022202320242025

Training seasonsPredicted blindFinal test — scored once, after all model decisions

The boom side — calling ceiling weeks

Start our five highest-ranked players every week — how often you got a ceiling game, against picking five startable players at random:

KLEG DAY43%CHANCE29%+14 pts vs chance pts

DSTLEG DAY34%CHANCE20%+14 pts vs chance pts

QBLEG DAY22%CHANCE17%+5 pts vs chance pts

RBLEG DAY40%CHANCE20%+20 pts vs chance pts

WRLEG DAY43%CHANCE20%+23 pts vs chance pts

TELEG DAY43%CHANCE21%+22 pts vs chance pts

POSWHAT DRIVES ITBOOM F1RECALLPRECISIONTOP-5 HIT (CHANCE)RANK CORR.

KSimulates every matchup kick by kick - field position, distance mix, kicker leg, conditions0.3844%33%43% (~29%)0.18

DSTReads the betting market - what the lines imply about scores, pressure and turnovers0.4265%31%34% (~20%)0.34

QBRecent form against the opponent defense and the game environment0.2940%23%22% (~17%)0.27

RBRecent usage and form against the opponent front and expected game script0.3952%31%40% (~20%)0.42

WRRecent usage and form against the opponent secondary0.3653%28%43% (~20%)0.37

TERecent usage and role against how defenses handle the position0.4160%31%43% (~21%)0.44

Boom calls (F1, recall, precision) are pooled over every 2025 regular-season week; top-5 hit and rank correlation grade the published ordering week by week. RB/WR/TE scoring is half-PPR with 4-pt passing TDs (QB is identical in every format). QB is our weakest call and we say so — 2025 was a cold year for quarterback booms (17% base rate) and ours came in under the range we expected.

The avoid side — our strongest calls

Half of weekly fantasy is dodging the disaster start — often the bigger half. It's also where these models grade out best: at every position, our bust calls score higher than our boom calls, topping out with DST's 53% precision at 62% recall. And the ordering holds at the bottom too — the five players the board ranks last each week bust above the base rate at every position, more than double it at RB and TE.

The five players we rank last every week— how often their game actually busted, against sitting five startable players at random:

KLEG DAY46%CHANCE39%+7 pts vs chance pts

DSTLEG DAY60%CHANCE38%+22 pts vs chance pts

QBLEG DAY47%CHANCE33%+14 pts vs chance pts

RBLEG DAY53%CHANCE23%+30 pts vs chance pts

WRLEG DAY54%CHANCE30%+24 pts vs chance pts

TELEG DAY68%CHANCE27%+41 pts vs chance pts

POSWHAT DRIVES ITBUST F1RECALLPRECISIONBOTTOM-5 HIT (CHANCE)

KSimulates every matchup kick by kick - field position, distance mix, kicker leg, conditions0.4751%43%46% (~39%)

DSTReads the betting market - what the lines imply about scores, pressure and turnovers0.5762%53%60% (~38%)

QBRecent form against the opponent defense and the game environment0.4959%42%47% (~33%)

RBRecent usage and form against the opponent front and expected game script0.4567%33%53% (~23%)

WRRecent usage and form against the opponent secondary0.4958%42%54% (~30%)

TERecent usage and role against how defenses handle the position0.5371%43%68% (~27%)

2025 final test, pooled over the season. Precision = when we flag an avoid, how often they actually busted; judge it against the 2025 bust base rates, which ran from about 23% (RB) to 39% (K) by position — 33–53% is real edge, not a guarantee. Bottom-5 hit = start the five players the board ranks last each week; the share that busted, vs picking five startable players at random. (Rank correlation isn't repeated here — the board is one ordering, already graded in the boom table.)

How live boards differ from the backtest

Tuesday boards are previews. They run on Tuesday-morning inputs — betting lines, weather forecasts and the expert consensus as they stood on Tuesday — so they are the actionable-for-waivers version, not the graded one.
Saturday boards are the record. Every in-season number on this page will come from the Saturday board, re-run on Saturday-morning lines, forecasts and consensus. Rows for teams playing on Thursday stay frozen at their Tuesday values on the Saturday board (their game already happened), are marked as such, and are graded at those Tuesday values.
Only pooled players are graded. A player is on the board only after showing startable recent production, so some booms happen off-board (breakout rookies, role changes). Watch-list names, previews and Sunday notes are never counted.

What the numbers mean

Recall

Of the games that actually happened — ceiling games on the boom side, disasters on the bust side — the share we flagged in advance. High recall means we rarely miss one.

Precision

When we make a call, how often it comes true. Judge it against the base rate: in 2025 booms happened 17-29% of the time by position and busts 23-39%, so precision above those numbers is real edge — not a guarantee.

F1 score

Recall and precision combined into one 0-to-1 number (their harmonic mean). It punishes cheating in either direction: flag everyone and precision collapses; flag almost no one and recall collapses. Best single number for comparing models.

Top-5 hit (chance)

Start our five highest-ranked players every week: the share that boomed. The number in parentheses is what you'd get picking five startable players at random — the gap between the two is the whole product.

Rank correlation

Line up our ordering against how players actually finished that week. 0 means our order told you nothing; 1 means it was perfect. Weekly fantasy is extremely noisy — nobody lives near 1, and anything above ~0.25 is meaningful signal.

What MID actually means

Not a prediction of an average game — it's the model declining to make a call. Neither the boom nor the bust probability clears our confidence threshold, so we say so instead of faking a lean.

⚖️

Also published honestly: our preseason "which kicker will lead the season" prediction is close to signal-free (year-over-year rank correlation ≈ 0). That's exactly why we built a weekly streaming product instead of a draft-a-kicker product.

Predictions are probabilistic, not guarantees. Kicker scoring has inherent randomness — we publish our misses. Not affiliated with the NFL. Not gambling advice.