Logistic Regression Markov Chain (LRMC)

Logistic Regression Markov Chain (LRMC) is a college basketball rankings system, designed to use only basic scoreboard data, including which teams played, which team had home court advantage and the margin of victory. It was originally designed by Joel Sokol and Paul Kvam and has been maintained and improved by Sokol and George Nemhauser, all three optimization and statistics professors …

Machine Learning Systems in Sports

I’m often asked about how to make accurate predictions and what tools I used to employ in the past. I’ve observed that this subject is not well understood in the NBA community, so I’ll try to provide more insight in this post. The Majority of people picked the Lakers against Dallas, right? Simulations, statistics, and gut could tell us the …

Martin Manley

Martin Manley has created NBA Efficiency, the first ever player evaluation metric which had been incorporated by NBA.com. In the late 1980’s, he wrote “Basketball Heaven” books in which he outlined his production ratings, statistical indexes which measure the overall production of players and teams. In the book, he discusses his formula and variations, and compiles indexes for all players …

Measuring Transition Defense

Dividing opponent’s fast break points by opponent’s steals might give us an idea of how teams execute “transition defense”.

MIT Sloan Sports Analytics Conference (SSAC)

SLOAN SPORTS ANALYTICS CONFERENCE – RECENT HISTORY In 2004, MIT Sloan and Daryl Morey initiated one of the first MBA programs with a sports analytics business class. This began a focus in sports business that was extended, when Daryl Morey and Jessica Gelman founded the MIT Sloan Sports Analytics Conference in the winter of 2006. In 2007, the inaugural sports …

Mocap Analytics

MOCAP Analytics is a Silicon Valley technology startup which has been acquired by Sportradar in 2017, developed an analytics platform to interpret the data, and provide relevant, actionable information to the team staff. NBA teams use Mocap in order to process all of the video tracking data. Using MOCAP’s platform, there’s an opportunity to share creative content that will give …

NBA CourtOptix

NBA CourtOptix collects advanced metrics, shot charts, and all kinds of video tracking stats in the same platform. Since the fans are targeted, CourtOptix combines advanced player tracking data and game highlights to present a more detailed breakdown of the game. With launching the CourtOptix, the NBA has partnered with Microsoft, which uses its Azure platform plus the AI (Artificial …

NBA Efficiency

NBA Efficiency, is a metric invented by Martin Manley, is being considered the first ever player evaluation metric which indicates player’s linear efficiency. PROS: NBA Efficiency does a nice job of explaining free agent salary. NBA Efficiency tells us about perceptions of performance. It just has some problems if our objective is to measure the impact a player has on …

NBA Play by Play Data

What does play-by-play data include? Traditional box score data shows per-game totals for players and for teams and reveals only a fraction of what happens in a game and that the information therein is often misleading, especially at defensive stats. At this point, Play-by-Play (PBP) data has been the main source of many advanced stats such as adjusted plus-minus. Play-by-play …

NBA Plus-Minus and Player Impact Metrics: The Complete Guide

Introduction to NBA Plus-Minus In the modern basketball era, NBA plus-minus and its derived metrics have become an useful tool for fans, for coaching staff to measure a player’s impact. Relying only on box score metrics such as points, rebounds, and assists are not enough. NBA Plus-Minus, a.k.a. +/-, simply keeps track of the net changes in the score when …

nba.com/stats (Formerly StatsCube)

StatsCube was a new data warehouse tool which the NBA released in 2009 for only its franchises. It is currently open to everyone and being known as “nba.com/stats“. By the 2009-10 season, StatsCube was made available to every team. It provided instantaneous statistical analysis, calculations and produce adjustable notifications and customized reports. StatsCube had in it every point, rebound, assist, …

Net Plus-Minus (Roland Rating)

Net plus-minus, aka unadjusted plus-minus, aka Roland Rating is invented by Roland Beech and measures the plus-minus statistics for a given player when the player is in the game relative to the plus-minus statistics when the player is NOT in the game. Net plus-minus combines offensive and defensive plus-minus. For example, if a team scores 115 points (per 100 possessions) …

Net Points

Net Points is a single-game performance analysis metric developed by ESPN Analytics Team to evaluate players more deeply and accurately than traditional stats. It uses play-by-play data to assign credit and blame for every play, considering the difficulty and context of each player’s actions. Net Points quantifies individual contributions like shots, assists, rebounds, turnovers, defensive plays, and their direct impact …

Neural Networks

Neural networks are one of the machine learning systems in sports. With the help of neural networks, datasets are learned by the system and hidden trends can be revealed for creating a competitive edge. Simulations and machine learning systems means a lot for sports analytics. The ability to apply statistics and rigorous mathematical models to provide instantaneous results is quickly …

New England Statistics Symposium NESSIS

NESSIS is an event in which statisticians from all over the world come together and present academical studies. NBA and other sports analytics community has been benefiting from NESSIS that many studies on statistics regarding professional sports are being introduced first time at NESSIS just like MIT Sloan Sports Analytics Conference. The first New England Statistics Symposium was held at …

Non-Scoring Player Possessions

Non-scoring player possessions would be a player’S missed field goals, plus free throws that weren’t rebounded by his team, plus his turnovers.

Offensive Conversion Rate

Offensive Conversion Rate measures the percentage of a player’s steals that result in a made basket or free throw attempts within 5 seconds. The reason for taking 5 seconds is to measure a player’s transition defense in terms of how frequently his steals lead to offensive production.

Offensive Efficiency

Offensive efficiency is the number of points a team scores per 100 possessions. In a game; “offensive efficiency” of a team is equal to defensive efficiency of the opponent team. Refer to the NBA team stats for any season’s offensive efficiency statistics.

Offensive Rating

Offensive rating, along with defensive rating is invented by Dean Oliver. Individual offensive ratings are constructed from the following two statistics: Scoring possessions, which represents the credit an individual gets for the times his/her team ends a possession and gives it back to the opponents. Individual points produced, which represents the credit an individual gets for the points that his/her …

Opta

Opta, founded in 1996, is currently a Perform Group company, which supplies data, statistics and information from over 30 different sports in around 70 countries. Opta already has a wide range of clients from media to betting, from professional clubs to governing bodies and are working on many projects where data analysis is a crucial part of their product offering. …

Pace

Pace is the total number of possessions a team uses in a game. Team minutes is 240 (5×48= 5 players on the court for 48 minutes) in a regulation game. 265 (=5×53) in a 1 OT game. 290 (=5×58) in 2 OT game. 315 (=5×63) in a 3 OT game. 340 (=5×68) in a 4 OT game Refer to the …

Per-Minute Ratings

Per-minute ratings evaluate a player’s performance more accurately than his per-game averages. The common notation for per-minute ratings is using per 36-minute, or per 40-minute stats.

Personal Foul Efficiency

Personal Foul Efficiency measures the ratio of steals plus blocks to personal fouls. Indicates how efficiently a player forces turnovers, removing the bias of jump-happy or slaptastic players who accumulate deceptive block or steal totals. This statistic can be deceiving, since fouls may increase with defensive effort, but it is still a useful measure for comparative analysis.

Play Percent

The metric that indicates the percentage of the time a team will score if not sent to the free throw line. Scoring possessions minus scoring possessions on which no field goal was made (only free throws), divided by possessions minus scoring possessions on which no field goal was made. Play Percent Formula= Field Goals Made/(Field Goals Attempted-Offensive Rebounds+Turnovers)

Player Efficiency Rating (PER)

PER is a player evaluation metric that boils down all of a player’s contributions into one number. John Hollinger‘s formula adds positive stats and subtracts negative ones through a statistical point value system. The average PER is set at 15. For more information about PER Calculation visit basketball-reference. As the PER largely measures offensive performance -while the calculation seems pretty …

Player Impact Estimate (PIE)

Player Impact Estimate aka PIE, is a metric to gauge a player’s all-around contribution to the game. Almost all statistical categories in the box score are involved in the PIE formula. PIE answers what % of the events in a game each player contributed. PIE is created by the NBA and often being compared to PER. Unlike PER, PIE calculation …

Player Impact Plus-Minus (PIPM)

Player Impact Plus Minus (PIPM) is a new kind of adjusted plus-minus metric that incorporates boxscore data “luck-adjusted” plus-minus data. The output of PIPM is an estimate a player’s value over the course of a season. Luck-adjusted methodology is created by Nathan Walker and uses more statistically predictive factors of a team’s offensive and defensive rating (points scored or allowed …