Pick a template to forkEvery card is a verified, editable starting point. Fork one, or start from scratch.

Team strength, quarterback accuracy, pressure, and weather vs the spread — the classic power-ratings edge, now with 10 signals instead of 3.

No graded picks yet

Fast-paced matchups quietly beat the total. Pace, explosive plays, and red-zone efficiency say when the scoreboard spins.

No graded picks yet

The market over-reacts to star injury news and under-rates backups. Real injury-impact signals find the overcorrections.

No graded picks yet

Wind, cold, and rain kill scoring more than the line admits. Real forecast data hunts overpriced totals in bad-weather games.

No graded picks yet

The flagship: 21 signals — team strength, efficiency, travel, injuries, weather, and where sharp money leans — blended and calibrated again…

No graded picks yet

Start from what the betting market already knows, then look for the small spots where the true win chance drifts from the price.

No graded picks yet

Opening scripts are planned all week — early-down success, pace, and drive quality predict the first half better than the full game.

No graded picks yet

Passing-yard props from tracking data: time to throw, receiver separation, pass-heaviness, pressure, and wind — a full range, not one numbe…

No graded picks yet

Receiving props live on routes and matchups: route depth, separation, pace, and game script set the real yardage range.

No graded picks yet

Rushing yards follow game script: efficiency on the ground, expected margin, and weather decide who actually carries the rock late.

No graded picks yet

DraftKings scoring loves pace, explosive plays, and red-zone chances. Project fantasy points where the environment does the heavy lifting.

No graded picks yet

Referee crews call games differently — some crews mean fewer points. A niche angle almost nobody models, built from 40-game crew histories.

No graded picks yet

Game-level NFL spread modeling. Bundles schedule, Vegas spread, Elo power ratings, weather + rest. XGBoost regression + quarter-Kelly staki…

No graded picks yet

Game-level NFL totals (O/U). Bundles pace, defensive efficiency and weather/wind features with a gradient-boosting regressor + variance-cap…

No graded picks yet

A model built on the thesis that Rest advantage should matter only when it is not paired with poor lagged continuity; trained with calibrat…

No graded picks yet

An ensemble model combining elo, pace, and weather features with a quantile xgb architecture and kelly fraction staking will outperform the…

No graded picks yet

A quantile-xgb model with team form, elo, and pace features, using a calibrated blend ensemble and kelly-fraction staking, will beat the in…

No graded picks yet

Games played in cold outdoor conditions with significant wind suppress scoring relative to the posted total — wind reduces passing efficien…

No graded picks yet

Back-to-back games suppress scoring as fatigue slows offensive execution. LightGBM quantifies how much a back-to-back depresses scoring rel…

No graded picks yet

First-half totals are a pure starter quality bet before bullpen erosion kicks in. Recent form and pitch-mix evolution determine whether sta…

No graded picks yet

The theory says that a player’s red-zone snaps and targets predict extra touchdown chances beyond what the betting line shows. The approach…

No graded picks yet

Bayesian Ridge captures uncertainty in assist predictions for playmakers when role changes or lineup shuffles create unstable baselines. Us…

No graded picks yet

Batters hit more doubles when facing fly-ball pitchers who give up soft contact. This model fuses pitcher xwOBA allowed, batter pull-rate,…

No graded picks yet

Primary playmakers on contending teams facing defensive-minded opponents generate assist totals CatBoost can predict with higher accuracy t…

No graded picks yet