A basketball fanatic and a math whiz want to do for basketball what Bill James and sabermetrics did for baseball, and their innovative way of parsing data could revolutionize game analysis, providing coaches with new insights while making the game more fun to watch.
Sabermetrics, for those who haven’t seen Moneyball, is the objective analysis of baseball using game stats. Billy Beane used it to revolutionize the Oakland A’s. Compared to baseball, though, basketball is much more dynamic, and ball movement becomes a key variable in success. Passing is one of the fundamentals of hoops, and in the upper ranks of the sport, turnovers — often the result of wayward passes — contribute to ticks in the win-loss column. Fast, agile passing can make or break a team.
More on Stats in Sports
Big Data Quantifies The Beautiful Game
Analytics Reveal 13 New Basketball Positions
Stats Prove Jordan’s Olympic Team Beats Kobe’s
Post-Interception ‘Momentum’ Is a MythThat’s why sabermetrics might not tell the entire story about what happens on the court. Researchers at Arizona State University, led by life science professor and basketball fan Jennifer Fewell and math professor Dieter Armbruster found an ideal model to explain the results of the 2010 NBA playoffs by simply keeping their eye on the ball. Their work opens the door to an entirely new line of sports analysis, from game-tape breakdown to highlight reels and augmented-reality visualizations.
To analyze basketball plays, Fewell and Armbruster used a technique called network analysis, which turns teammates into nodes and exchanges — passes — into paths. From there, they created a flowchart of sorts that showed ball movement, mapping game progression pass by pass: Every time one player sent the ball to another, the flowchart lines accumulated, creating larger and larger and arrows.
Using data from the 2010 playoffs, Fewell and Armbruster’s team mapped the ball movement of every play. Using the most frequent transactions — the inbound pass to shot-on-basket — they analyzed the typical paths the ball took around the court.
Network analysis of the Chicago Bulls, showing the majority of ball interaction remained with the point guard. Image: Jennifer Fewell and Dieter Armbruster
Network analysis of the Los Angeles Lakers shows the team is far more likely to distribute the ball among more players, using the “triangle offense.” Image: Jennifer Fewell and Dieter ArmbrusterFor most teams, the inbound pass went primarily to the point guard, generally a team’s best ball handler. But point guard-centric, such as the Bulls, didn’t fare well in the 2010 playoffs, the researchers told Wired.
On the other hand, the Los Angeles Lakers — which won the 2010 NBA championship — distributed the ball more evenly than their rivals, embracing what Phil Jackson calls the “triangle offense,” a technique pioneered by Hall of Fame coach Sam Barry. The basic idea is simple: Maintain balanced court spacing so any player can pass to another at any point.
In their model, Fewell and Armbruster found a mathematical explanation for why the triangle offense works — the point guard was no longer the only player feeding passes to fellow players; his teammates were just as likely to take on that role. With more potential passers, there are more potential paths for the opposition to defend.
To quantify their results, published in the journal PLOS ONE, the researchers derived the entropy, or measure of system disorder, for each team during each game. In six of the eight first rounds, winners had higher team entropy, and therefore more randomness, than losers. Though the sample size of teams in the NBA playoffs may be small, the data suggest a possible relationship between quick, unpredictable ball movement and success in games.
“[It seems] entropy wins games,” Armbruster told Wired.
Not everyone is convinced. Critics say the triangle offense marginalizes point guards. The loudest critic might just be Lakers general manager Mitch Kupchak, who boldly told reporters the triangle offense was not only wrong for a Lakers team helmed by All-Star point guard Steve Nash, but any Lakers team at all.
Triangle offense aside, there are many applications for the modeling Fewell and Armbruster used to dissect it. Krossover Intelligence is working on some of the most promising. James Piette, v.p. of analytics, said the company has used a similar approach in a video playback system that could revolutionize game tape analysis.
“We want to help coaches win,” Piette said.
All of Krossover’s videos are searchable, and their technology is sophisticated enough to create computer visualizations showing what players did — and, better yet, what they should have done.
Piette has been a stats geek since he was 18, when he wrote an artificial intelligence poker program. He’s got a triple major in mathematics, economics and computer science, and a PhD in statistics. Midway through his doctoral program, Piette met Vasu Kulkarni, a self-described basketball junkie who was just launching Krossover, a company obsessed with sports statistics. The team excels at breaking down game tape using analysis similar to, yet distinct from, what Fewell and Armbruster developed. They’ve already signed up the Caltech men’s basketball team.
“We were looking for program that would streamline process of video breakdown and stat analysis,” head coach Oliver Eslinger told Wired. He said Krossover is easier to use than his former method, which consisted of scrutinizing DVD game footage and recording results in a computer spreadsheet.
Because Krossover lets you diagram and breakdown every possession, coaches no longer have to have to fast-forward or rewind game film to show a player’s performance during a game. Need to know every shot-on-basket for John Doe during a particular game? The answer is one click away on Krossover’s platform.
Because Krossover can repurpose some of the video data — with permission of the original team, of course — the company could create the next-gen highlight reels or visual recruiting database. For instance, coaches may be able to use the system to quickly understand how well a particular blue chip recruit performs against the 1-3-1 zone defense when on the road. Or, better yet, the program might show how much a highly overlooked player contributes to overall team play, leading to coaches recruiting the prospect.
In retrospect, Moneyball propelled the field of sports statistics more than Piette first expected. Before the book and movie became popularized, he had trouble publishing his work, because the academic community viewed sports as just a game, not serious science, Piette guesses. But the MIT Sloan Sports Analytics Conference is now packed, he told Wired.com, offering people places to publish their sports-related results in peer-reviewed publications.
Perhaps the only problem is: now everyone who took Stats 101 thinks they are an analyst. But stats aren’t linear, Piette says, and the simple regression methods that most learned won’t work. The type of rigor needed to crack these sports statistics problems are only taught in PhD programs. And while none currently exists, Piette hopes for specific advanced degrees in sports analytics one day.
While fans direct cheers that fill sports arenas toward athletic giants such as LeBron James or Kobe Bryant, bright statisticians still sit in the shadows. But when these mathematical stars begin helping LeBron improve his game, it’s certain they’ll hear more and more of the applause.
