Navigation
Academic Basketball Articles
Coming Soon: Research Involving BigDataBall.com Data
Using Scouting Reports Text To Predict NCAA → NBA Performance
Draft decisions by National Basketball Association (NBA) teams are notoriously poor. Analytics can help but are often dismissed for being too overfit, complex, risky, and incomplete. To address these concerns, we train separate leave-one-out random forests machine learning models for each collegiate NBA prospect from 2006 through 2019 with a conservative utility function on a novel comprehensive dataset including the raw text of scouting reports, combine measurements, on-court stats, mock draft placements, and more. Despite being unable to draft high school or international players, the resulting model outperforms the actual decisions of all but one NBA team, with an average gain of $100 million. Target shuffling shows that the model does not overfit and feature shuffling shows that handedness and ESPN mock draft rating, but not other mock drafts, are most important. NBA teams may be missing value by not following a disciplined, model-driven, prescriptive analytics approach to decision making.Available on JBA.
Citation: Maymin, Philip Z. (2021), "Using Scouting Reports Text To Predict NCAA → NBA Performance" Journal of Business Analytics DOI: 10.1080/2573234X.2021.1873077
Wage Against the Machine: A Generalized Deep-Learning Market Test of Dataset Value
How can you tell if a particular sports dataset really adds value? The method introduced in this paper provides a way for any analyst in almost any sport to attempt to determine the additional value of almost any dataset. It relies on the use of deep learning, comprehensive historical box score statistics, and the existence of betting markets. When the method is applied as an illustration to a novel dataset for the NBA, it is shown to provide more information than regular box score statistics alone, and appears to generate above-breakeven wagering profits.
Citation: Maymin, Philip Z. (2019), "Wage Against the Machine: A Generalized Deep-Learning Market Test of Dataset Value," International Journal of Forecasting, Special Issue on Sports Forecasting, 35:2, 776-782.
Presentations
- Sports Analytics Innovation Summit, September 10, 2015
Media and Press
- When Deep Learning Met Vantage Data, December 27, 2015
Blogs and Discussions
- APBRmetrics (5 comments)
The Automated General Manager: Can an Algorithmic System for Drafts, Trades, and Free Agency Outperform Human Front Offices?
An automated system using machine learning methods, applied to a broad historical database, while avoiding survivorship bias, and for a variety of performance metrics, is developed and tested against actual historical human performance, for drafts, free agency, and trades, in the National Basketball Association (NBA). The resulting system is robust, comprehensive, realistic, and does not overfit information from the future. Backtested over ten years in a partial equilibrium non-zero-sum setting where only one team can benefit from its recommendations, the automated general manager would have outperformed the actual historical production of every single team, by substantial margins. From draft decisions alone, the average team lost about $130 million worth of on-court productivity relative to what they could have had with the automated general manager in total over the decade; this shortfall represents a quarter of the average franchise value. Thus, the general management of sports franchises may benefit substantially from automation.Citation: Maymin, Philip Z. (2017), "The Automated General Manager: Can an Algorithmic System for Drafts, Trades, and Free Agency Outperform Human Front Offices?" Journal of Global Sport Management, 2:4, 234-249.
Presentations
- Cornell Financial Engineering Manhattan Seminar, April 11, 2018 video
Blogs and Discussions
- Marginal Revolution (31 comments)
- Wages of Wins (8 comments)
- Sports Analytics Blog
Media and Press
- Medium: The Cost Of Bad Drafting
- Wall St. Cheat Sheet: The 6 Best Drafting Teams in the NBA, And the High Cost of Poor Picks
- NYU Press Room: FRE Professors Take Two of Top Five SSRN Spots
SSRN Top Ten Download Lists
- Weekly Top 5 - May 16, 2014
- ERN Subject Matter eJournals
- Economics Research Network
- Labor eJournals
- Labor: Personnel Economics eJournal
- All SSRN Journals
Acceleration in the NBA: Towards an Algorithmic Taxonomy of Basketball Plays
I filter the 25-frames-per-second STATS/SportVu optical tracking data of 233 regular and post season 2011-2012 NBA games for half-court situations that begin when the last player crosses half-court and end when possession changes, resulting in a universe of more than 30,000 basketball plays, or about 130 per game. To categorize the plays algorithmically, I describe the requirements a suitable dynamic language must have to be both more concise and more precise than standard X's and O's chalk diagrams. The language specifies for each player their initial starting spots, trajectories, and timing, with iteration as needed. A key component is acceleration. To determine optimal starting spots, I compute burst locations on the court where players tend to accelerate or decelerate more than usual. Cluster analysis on those burst points compared to all points reveals a difference in which areas of the court see more intense action. The primary burst clusters appear to be the paint, the top of the key, and the extended elbow and wing area. I document the most frequently accelerating players, positions, and teams, as well as the likelihoods of acceleration and co-acceleration during a set play and other components intended to collectively lead to an algorithmic taxonomy.Available on SSRN.
Citation: Maymin, Philip Z. (2013), "Acceleration in the NBA: Towards an Algorithmic Taxonomy of Basketball Plays," Working Paper.
Citation: Maymin, Philip Z. (2013), "Acceleration in the NBA: Towards an Algorithmic Taxonomy of Basketball Plays," Proceedings of the 7th Annual MIT Sloan Sports Analytics Conference.
Presentations
- The Innovation Enterprise Sports Analytics Summit, September 10-11, 2014
- 7th Annual MIT Sloan Sports Analytics Conference, March 1-2, 2013
- Grantland
Media and Press
- SAP: "X-Y Marks The Spot: SportVu Cameras Are Changing The World of Stats"
- Yahoo! Sports: "Maymin's work could lead to a fresh new method of quantifying in-play execution, which is just about always the division between good NBA teams and bad ones."
- Sports Illustrated: "Maymin draws all kinds of conclusions from the data collected, but most relevant were his findings regarding Pierce. In the data from the 2011-12 season (the extent of Maymin's set), Pierce rated as one of the league's most frequent accelerators, comparing favorably to the likes of Kevin Durant and Dwyane Wade."
- Sports Illustrated: The Fundamentals
- Deadspin
- ESPN
Blogs and Discussions
SSRN Top Ten Download Lists
- ERN: Statistical Decision Theory; Operations Research (Topic)
Individual Factors of Successful Free Throw Shooting
(with Allan Maymin and Eugene Shen)
We use three-dimensional optical tracking data on the 25-frames-per-second positional data of 2,400 free throw shots by the twenty players with at least twelve tracked makes and twelve tracked misses over the course of the 2010-2011 NBA season, fit each trajectory to a comprehensive physics model to find the implied backspin, initial launch height, velocity, angle, and left-right deviation, and examine the differences of those five factors between makes and misses for each player with sufficient attempts in our sample. We find that usually one or two factors are most responsible for a given player's misses, but the particular factors at fault differ across players. Thus, the causes of successes and failures in free throw shooting are idiosyncratic. This framework may also be useful in analyzing jump shots taken during the game.
Available on SSRN and on JQAS.
Citation: Maymin, Allan; Maymin, Philip Z.; Shen, Eugene (2012), "Individual Factors of Successful Free Throw Shooting," Journal of Quantitative Analysis in Sports 8:3, doi:10.1515/1559-0410.1414.
Data
The data used in this paper has been made publicly available. Download CSV.
The 2,400 rows after the header row each represent the best-fit parameters of a single free throw trajectory following the methodology described in the paper.
The columns are: Player Name, Backspin (w), Launch Height (z), Launch Velocity (v0), Launch Angle (a), Left-Right Deviation (lr), and Made/Missed (result; 1=make, 0=miss).
Media and Press
- Fox News: Study reveals why NBA players miss free throws
- Sina Sports: 3D手段能让魔兽不再尴尬？ 数据揭示罚球不中原因
SSRN Top Ten Download Lists
- Human Resource Management & Organizational Behavior eJournal
- Individual Issues & Organizational Behavior eJournal
- MRN Organizational Behavior Research Network
- ORG Subject Matter eJournals
- ORG: Biographical Issues, Ability, & Learning (Topic)
- ORG: Employee Performance Appraisal Systems (Topic)
NBA Chemistry: Positive and Negative Synergies in Basketball
(with Allan Maymin and Eugene Shen)
We introduce a novel Skills Plus Minus ("SPM") framework to measure on-court chemistry in basketball. First, we evaluate each player's offense and defense in the SPM framework based on three basic categories of skills: scoring, rebounding, and ball-handling. We then simulate games using the skill ratings of the ten players on the court. The results of the simulations measure the effectiveness of individual players as well as the 5-player lineup, so we can then calculate the synergies of each NBA team by comparing their 5-player lineup's effectiveness to the "sum-of-the-parts." We find that these synergies can be large and meaningful. Because skills have different synergies with other skills, our framework predicts that a player's value is dependent on the other nine players on the court. Therefore, the desirability of a free agent depends on the players currently on the roster. Indeed, our framework is able to generate mutually beneficial trades between teams. Other ratings systems cannot generate mutually beneficial trades since one player is always rated above another. We find more than two hundred mutually beneficial trades between NBA teams, situations where the skills of the traded players fit better on their trading partner's team.
Available here or on SSRN or on SSAC. Abstract available at IJCSS.
Citation: Maymin, Allan; Maymin, Philip Z.; Shen, Eugene (2013), "NBA Chemistry: Positive and Negative Synergies in Basketball," International Journal of Computer Science in Sport 12:2, 4-23.
Citation: Maymin, Allan; Maymin, Philip Z.; Shen, Eugene (2012), "NBA Chemistry: Positive and Negative Synergies in Basketball," Proceedings of the 6th Annual MIT Sloan Sports Analytics Conference.
Presentations
- 6th Annual MIT Sloan Sports Analytics Conference, March 2-3, 2012
Media and Press
- New York Times: Off the Dribble
- ESPN TV: Numbers Never Lie
- CBS Sports
- ESPN TrueHoop (2012)
- Basketball Prospectus (2012)
- ESPN TrueHoop (2011)
- Grantland: The Outstanding Mind-Bending Basketball Synergy Machine
Blogs and Discussions
- APBRmetrics (35 comments)
- Paul Kedrosky
SSRN Top Ten Download Lists
- Behavioral & Experimental Finance eJournal
- Decision Analysis eJournal
- Decision Making, Organizational Behavior & Performance eJournal
- Econometrics: Applied Econometric Modeling in Microeconomics eJournal
- ERN: Criteria for Decision-Making under Risk & Uncertainty (Topic)
- ERN: Team Theory (Topic)
- ERN: Teams (Topic)
- ERN: Sports Economics (Topic)
- FEN: Behavioral Finance (Topic)
- Labor eJournals
- Labor: Human Capital eJournal
- Labor: Personnel Economics eJournal
- Management Research Network
- Microeconomic Theory eJournals
- MRN Operations Research Network
- MRN Organizational Behavior Research Network
- Microeconomic Theory eJournals
- OPER Subject Matter eJournal
- OPER: Single Decision Maker (Topic)
- ORG Subject Matter eJournals
- ORG: Groups & Teams (Topic)
- Organizations & Markets: Personnel Management eJournal
- Organizations & Markets eJournals
How Much Trouble is Early Foul Trouble?
(with Allan Maymin and Eugene Shen)
We analyze a large and comprehensive play-by-play dataset of professional games in the National Basketball Association using tools from financial economics to explore the optimality of strategically idling resources in the face of uncertain future demand. We find that starters ought to be idled by the coach on a "Q+1" basis, meaning that a starter has one more foul than the current quarter, when the future option value is high or the value of the replacement player is high. We use a novel win-probability approach that can be easily extended to other applications.
Available on SSRN and IJSF. Data source: BasketballGeek. Download PDF.
Citation: Maymin, Allan; Maymin, Philip Z.; Shen, Eugene (2012), "How Much Trouble is Early Foul Trouble?", International Journal of Sport Finance 7:4, 324-339.
Citation: Maymin, Allan; Maymin, Philip Z.; Shen, Eugene (2011), "How Much Trouble is Early Foul Trouble?", Proceedings of the 5th Annual MIT Sloan Sports Analytics Conference.
Presentations
- 5th Annual MIT Sloan Sports Analytics Conference, March 5, 2011
- Southern Economic Association, November 19, 2011
Blogs and Discussions
- Mind Your Decisions
- Paul Kedrosky
- YCombinator Hacker News (15 comments)
- Baylor Fans (3 comments)
- Fighting Illini Basketball (12 comments)
- APBRmetrics
- Marginal Revolution (1 comment)
Media and Press
- The Wages of Wins Journal: "Adjusting Priors in Science, Basketball, and Life" by Allan Maymin, Philip Maymin, and Eugene Shen
- Slate: The Truth About Foul Trouble
- Basketball Prospectus: "Rethinking Foul Trouble" by Kevin Pelton
- ESPN TrueHoop: "How much trouble is early foul trouble?" by Brian Robb
- ESPN TrueHoop: "Research: Bench starters with fouls because they play poorly" by Henry Abbott
- The Atlantic: "NBA Coaches Should Yank Starters in Foul Trouble, Say Economists" by Derek Thompson
SSRN Top Ten Download Lists
- Behavioral & Experimental Finance (Editor's Choice) eJournal
- Behavioral & Experimental Finance eJournal
- FEN: Behavioral Finance (Topic)
- Economics Research Network
- Financial Economics Network
- ERN Subject Matter eJournals
- FEN Subject Matter eJournals
- ERN: Other Microeconomics: Decision-Making under Risk & Uncertainty (Topic)
- Microeconomic Theory eJournals
- Microeconomics: Decision-Making under Risk & Uncertainty eJournal
Archived Articles for Basketball News Services
From about January 2004 through May 2005, I was an Editor for Basketball News Services, covering the NBA for Hoopsworld.com. I was credentialed with the New Jersey Nets.
In that time, I wrote more than 600 articles, almost all of which are archived here:
- 81 weekly articles (longer, more analytic columns)
- 518 daily articles (shorter, team-specific pieces)
NBA Mysticism: Prophecies Fulfilled and Fortunes Told
A collection of some of the longer, more analytical articles is now available in print.  |
Prophecies Proved Prescient for the NBA
Telling the NBA's Fortune
Maybe it is a way to experience the present from the perspective of the past. Or maybe it is the first step in viewing basketball as a religious experience. Available on Amazon.com. |