alleygorithm
player impact + groups
PlayersTeamsGroupsGamesTrends
alleygorithm
player impact and winning groups

NBA analytics grounded in win probability, player impact, and the groups that have actually driven winning.

PlayersTeamsGroupsGamesTrendsHow it worksDevelopersPro
WPA-powered analytics from play-by-play data

ABOUT

Measuring who contributes to winning, from the possession up.

Alleygorithm is a basketball analytics system built on win probability added (WPA). Rather than counting box score events, the current production system models the probability of winning across the play-by-play stream, then attributes changes in that probability to the players on the court.

The product is intentionally built around three outputs: individual impact, group contribution, and confidence. That keeps the public experience readable even when the underlying modeling stack is more complex.

What The Backtests Actually Supported

0.1625 Brier
The production win-probability model beat the simple baseline on holdout.

Full remote holdout runs on April 1, 2026 kept the sequence model as the production path over the logistic event baseline.

0.0770 pair r
Raw pair contribution beat every interaction-style alternative we tested.

Cross-season backtests on April 2, 2026 showed raw pair WPA-style contribution beating residual, RAPM, and embedding variants.

Contribution-first
That is why the public product centers on player impact and group contribution.

Surplus and other research-only interaction fields stay secondary until new untouched holdout evidence says otherwise.

What Ships Today

Sequence win probability

The engine models win probability from play-by-play state, then turns each possession into a change in win probability.

Ridge attribution

Player impact is assigned with regularized regression, where the coefficients serve as the individual baseline for public scoring.

Multi-level group scoring

Players, pairs, trios, quartets, and lineups are scored in one system, with raw group contribution surfaced publicly and shrinkage/confidence keeping the leaderboard readable.

How The Scores Are Built

01
Win Probability Model

Every NBA possession changes the odds of winning. Our model watches the play-by-play and measures exactly how much each possession moved win probability — that swing is called WPA (Win Probability Added).

02
Player Attribution

When a possession swings the game, who deserves credit? We use ridge regression to fairly split the impact among the 10 players on court, controlling for teammates and opponents. Think of it as: "how much better does this player make things, all else equal?"

03
Multi-Level Scoring

We score every player, pair, trio, quartet, and lineup. Individual scores use the regression (most reliable). Group scores use raw WPA when those players share the court. Scores are stabilized with confidence-based shrinkage so low-sample-size outliers don't dominate the rankings.

04
Grades and Context

Raw numbers are hard to interpret, so every score gets a letter grade (A+ to F) based on percentile rank, a confidence level (how much data we have), and offensive/defensive splits. The goal: you should always know both what the number says and how much to trust it.

What Is Roadmap, Not Product

Richer interaction modeling

Learn fit beyond additivity with embedding and graph-based layers when they produce more stable public signal.

Lineup and trade simulation

Turn validated player impact and group contribution into a decision product for rotations, roster construction, and hypothetical moves.

Context slices

Expand into more specific use cases like play-type group context, matchup context, and defensive fit.

FAQ

How is this different from traditional plus/minus?

Plus/minus measures point differential while you're on court. WPA measures how much the win probability changed, weighting high-leverage moments more. Our Shapley attribution then fairly splits credit, while plus/minus conflates your impact with your teammates'.

Why do some great players rank lower than expected?

WPA captures context. A player on a dominant team may have fewer high-leverage possessions because the game state is already stable. The public scores also apply shrinkage, so lower-volume players get pulled toward the middle.

What does surplus mean for pairs and lineups?

Surplus measures whether a group performs better or worse than you'd expect from adding up the individual players. It is useful as a secondary research read, but the public product still centers the observed contribution itself.

What do the Off/Def splits show?

Offensive and defensive impact are computed separately using independent ridge regressions on possessions where the player's team has the ball vs. when they're defending. This isolates individual contribution on each side, controlling for teammates and opponents.

How often is the data updated?

The operating target is a fresh promoted score artifact on a daily cadence, while heavier WP retraining happens on a slower review cycle. The footer shows the latest promoted data currently being served.

Explore the data