Advanced NBA analytics,
and home of Estimated Plus-Minus.
Player-impact ratings, machine-learned game and stat predictions, advanced and traditional stats, and interactive dashboards for every game, player, and team.
Home of Estimated Plus-Minus (EPM)
EPM is a highly optimized, predictive player impact metric that leverages all available data (including player tracking data), incorporates knowledge about how each underlying stat stabilizes, and accounts for key predictive factors to estimate impact at any point in time. Click here to see more players.
Machine-Learned Projection System
The stats that feed EPM are individually optimized via machine learning to weight past games appropriately in predicting next game values. These stats handle the question about sample size for you by distinguishing real change from random fluctuations. The result is an estimate of true skill at each point in time. Here is Anthony Edwards' estimated skill in points / 100 possessions over his career.
Points per 100 Poss.
Team EPM: Player-Driven Team Ratings
Team ratings powered by EPM offer greater accuracy than traditional team ratings, and are more flexible at the start of the season, when there are injuries, and following trades. Additionally, the Strength of Schedule is more precise, reflecting the players who participated in previous games. Here are the top 5 teams right now. Click here to see more.
EPM-based Game Predictions
A game-optimized version of EPM is used to generate win probabilities for all regular season and playoff games. Game predictions update frequently based on available information about who will play in the game and are more accurate than traditional ratings in predicting game outcomes. Click here to see current game predictions.
| Final | Win Prob. | pScore | Score | ||
|---|---|---|---|---|---|
| 10 | Suns | 36% | 112 | 107 | |
| 3 | Hornets | 64% | 116 | 127 | |
| Final | Win Prob. | pScore | Score | ||
|---|---|---|---|---|---|
| 19 | Timberwolves | 30% | 105 | 108 | |
| 5 | Pistons | 70% | 112 | 113 | |
| Final | Win Prob. | pScore | Score | ||
|---|---|---|---|---|---|
| 14 | Lakers | 21% | 107 | 96 | |
| 1 | Thunder | 79% | 118 | 139 | |
| Final | Win Prob. | pScore | Score | ||
|---|---|---|---|---|---|
| 6 | Cavaliers | 71% | 118 | 118 | |
| 21 | Warriors | 29% | 111 | 111 | |
Boxscore Predictions
Optimized predictions for each player stat and game are made possible by the machine-learned estimated skill models. Here is an abbreviated boxscore, with predicted values below actual values, and green circles indicating an exact hit. Premium subscribers can enter custom minutes for each player updating predictions for player stats and the overall score and win probability.
| PLAYER | MIN | PTS | REB | AST | STL | BLK | 3P | 3P% |
|---|---|---|---|---|---|---|---|---|
Victor Wembanyama C
·
7'4" 235
·
22.4 | 39 35 | 26 24 | 4 13 | 3 3 | 1 1 | 2 4 | 2-5 2-5 | 40% 34% |
Devin Vassell SF
·
6'5" 200
·
25.7 | 36 36 | 20 13 | 7 5 | 2 2 | 4 1 | 0 1 | 3-6 2-7 | 50% 36% |
Julian Champagnie PF
·
6'7" 217
·
24.9 | 35 33 | 10 11 | 5 6 | 2 1 | 1 1 | 1 0 | 2-8 2-6 | 25% 37% |
Stephon Castle SG
·
6'6" 215
·
21.6 | 35 36 | 14 17 | 5 6 | 7 7 | 1 1 | 2 0 | 1-5 1-4 | 20% 32% |
De'Aaron Fox PG
·
6'3" 185
·
28.4 | 31 29 | 15 15 | 7 3 | 6 5 | 1 1 | 0 0 | 1-6 1-4 | 17% 33% |
Live Game Dashboards
Game scores, boxscores, and advanced stats update in real-time for each game. Win probabilities update with each event and account for each player's FT% skill. Interactive density shot charts, advanced team matchup stats, and boxscore stats are all live. Check out the full dashboard for the Cavs-Pacers game here.
Live Win Probability
Additional Features
Traditional & Advanced Stats
Traditional and advanced stats are available throughout the site. Set your preferred default data type — per-game, per-75, or advanced — and your choices for showing ranks and percentiles are saved automatically.
Powerful Interactive Dashboards
Intuitively command your view of the data by clicking on dynamic tables and beautiful visualizations for quick insight into player, team, and game stats and predictions.
Playoff Probabilities
Predicted win totals, playoff seeding probabilities, and the chance of winning each round is produced from tens of thousands of nightly simulations using EPM-powered game prediction models.
REST API Access
Programmatically pull EPM, E-Skills, season and team ratings, game win probabilities, and boxscore predictions across all available dates and seasons. Click here for the full API documentation.



