Chasing Perfection: A Behind-the-Scenes Look at the High-Stakes Game of Creating an NBA Champion (4 page)

Today, thanks to modern technology and a couple of decades of thinking about these types of questions, we’re moving closer to legitimate answers. In 2001, though, things really boiled down to a handful of really smart people bouncing numbers and ideas and theories off each other; given the much more limited data available at the time, there was no real way to test accuracy. In one of Oliver’s posts, he wrote about tracking a specific game for defensive stats analysis purposes, and “hoping TNT doesn’t cut away” from the game so he wouldn’t lose
any of his data.

So, whenever a new stat or approach came along, there was significant exploration—and disagreement—about its meaning, especially when it came to outlier cases.

“One of the memorable discussions that I’ve talked about in the past was the Timberwolves PR crew—the person who does their game notes was a friend of mine—they started including Kevin Garnett’s net plus-minus in their game notes,” Pelton said. “This was around his MVP season, and it was preposterous. It was like a plus-20 differential when he was on the court versus off the court. And people were like ‘No, this is preposterous. There’s no way one player can be that valuable,’ so it was kind of difficult to wrap your mind around that at the time because there was no context for it. There was no history to compare it to. Obviously, there is now, and [it] quickly became [available] when Roland Beech started putting it on the
82games.com
site. So that’s sort of [an example] of breakthroughs and difficulties that these different concepts created.

“I think [discussions] could certainly be a bit contentious. There are a lot of opinionated people in this field. That certainly hasn’t changed. A fundamental level of respect [existed, though]—especially for those who had contributed over an extended period of time and we’d seen the way their thought process worked.”

While in today’s professional sports, teams are more frequently hiring independent researchers and/or writers to help with their analytics evaluations, many of these formative discussions were happening prior to the Red Sox hiring James and well before Oliver was hired by the SuperSonics. The idea of moving these types of analyses into the mainstream and then getting hired to implement them for a sports franchise wasn’t very reasonable at the time.

“I’m sure it was for some people, but it seemed too big of a goal,” Pelton said of the sentiments of those participating. “The idea of getting people that understand the concept of true shooting percentage in there would be a big thing. And obviously,
Moneyball
kind of
accelerated things and showed the possibilities in another sport, and that kind of raised the bar in a way.

“There was a discussion in the intro [of the first Basketball Prospectus we did for the 2009–10 season]—I wrote my own intro—and I think there were eight teams at that point who had someone working for them in the front office or as a consultant to the organization. Now it’s probably twenty-eight or something like that, in a really short period of time.”

Despite all of the brainpower working to unlock basketball’s deepest secrets, implementation hasn’t been the smoothest path. There are so many hurdles to overcome beyond whether someone can actually collect and analyze the data properly to come up with new, innovative solutions to a basketball problem. Many of those challenges involve communication across nonmath specialists and, at the end of the day, impacting an extremely dynamic sport played by human actors who are not capable of flawless implementation of strategy, even if the strategy itself somehow is flawless.

Still, Pelton thinks back to the formative days on the board, where everything was new and exciting and still really foreign in a lot of ways, and appreciates how far things have already come.

“It’s kind of easy sometimes in the process to just see incremental changes and not notice them that much,” he said, “and also see the setbacks and get discouraged by them, but when you actually take those opportunities and can step back and look at the bigger picture and the context of everything, it’s really crazy how quickly this has happened.

“I mean, the similar revolution in baseball took a couple of decades, at least, and this took about half the time, in part because [baseball] helped pave the way.”

An October 2005 article in
Sports Illustrated
by Chris Ballard helped announce the arrival of what we now accept as the modern analytics-enhanced basketball world, and the piece doubles as a genealogy of many of today’s top NBA
coaching and management thinkers.

Beyond discussing some of Oliver’s work with Seattle, the article mentions twenty-nine-year-old Sam Presti, who was an assistant general manager with the San Antonio Spurs at the time and now is the general manager with the Oklahoma City Thunder. He’s widely cited as one of the sharpest front office people in the league, has an extremely strong draft track record, and also was at the center of perhaps the most impactful trade decision of this decade. It also introduces twenty-seven-year-old Sam Hinkie, who then was a special assistant to Houston Rockets owner Carroll Alexander, and now is the general manager of the Philadelphia 76ers, where he has been the chief protagonist in one of professional sports’ most debated team-rebuild strategies.

Additionally, it mentions San Antonio Spurs head coach Gregg Popovich. Popovich, of course, is in the discussion as the greatest head coach in NBA history, having won five NBA championships in San Antonio while churning out annual fifty- and sixty-win seasons. He’s also responsible for the NBA’s newfound appreciation of resting players and more balanced minute distributions across his roster, and is the figurehead for what is the most secretive analytics-friendly franchise in the league.

It also goes into some depth about thirty-one-year-old Boston Celtics senior vice president of operations Daryl Morey, who has since become the public face of NBA analytics. He helped found the wildly popular and influential Sloan Sports Analytics Conference (Morey has an MBA from MIT’s Sloan School of Management) while implementing increasingly sophisticated playing and personnel strategies as the general manager of the Houston Rockets.

In the subsequent decade or so since that article ran, the entire landscape has continued to evolve and morph into what we see today (with much of it continuing to be proprietary and unseen by the public). There’s way more money involved in the NBA today than even ten years ago, and teams have to work harder and harder to find and maintain competitive edges. How they’re doing so varies wildly from team to team, and heavily involves state-of-the-art technology to try to move ever closer to solving an impossibly complex and nuanced sport.

CHAPTER 2

The Basketball Technology Revolution

            
The power of having good algorithms is that it’s like you have a million pairs of eyes watching every single game. . . . It’s as if you have someone who has watched every single second of your opponent’s game and you can get very complete scouting, or every single second of a particular player that you’re trying to scout.

—Rajiv Maheswaran, CEO and cofounder, Second Spectrum

O
ne of the major epicenters of basketball’s ongoing technology movement spent some of its formative months in 2014 about a mile or so from Staples Center, in a hybrid work/live high rise on Los Angeles’s tony Wilshire Boulevard. While the building’s marble-adorned lobby with the make-your-own-espresso machine, as well as the rooftop pool and Jacuzzi, suggested hints of decadence, the crowded second-floor office of Second Spectrum didn’t match that anticipated standard.

The hall the office was located on was more traditionally apartment building-esque, with rows of closed doors on either side, and the sounds of hip hop pulsating from a room a few doors down. Inside, the one-room headquarters already was straining to handle the
company’s growth. It was shaped like a flat-bottomed
U,
with a reception desk (
sans
receptionist on this occasion) somewhat awkwardly lodged near the doorway in front of the right prong. Rows of minimalist desks lined the walls on both sides of that prong. In the back right corner was tucked Rajiv Maheswaran, the company’s CEO and cofounder, who with his team is starting to fundamentally change the way many think about professional basketball, from teams and players to fans watching the games.

Maheswaran and Yu-Han Chang were both computer science faculty at University of Southern California when they brainstormed an idea to track NBA player data, which turned into a research paper submission for the
2012 Sloan Sports Analytics Conference. The paper, which used player- and shot-tracking data along with machine-learning techniques, redefined what was then known about rebounding. It broke down the process of collecting missed shots into functions of initial on-court positioning, the hustle to pursue the ball once it came off the rim, and the conversion of opportunities to secure a rebound. The work won the conference’s best paper honors, and helped earn the duo the attention of some NBA teams. They and a third colleague, Jeff Su, formally launched Second Spectrum in 2013.

Feeding off the NBA’s new initiative with SportVU motion capture cameras that capture every movement on the court, Second Spectrum set out to interpret mountains of raw data, then layer video and/or graphics over it to serve a variety of constituents. By August 2015, the company, which has a staff literally composed of rocket scientists, was employed by nine of the NBA’s thirty teams, and was starting to marry data, technology, and presentation in landmark and
visually unique ways.

Teams were using them as a third-party provider to help enhance on-court strategy, and Second Spectrum also was translating in-game plays into statistic-heavy motion-enhanced graphics, so fans attending games could see things like the projected point values of the various pass and shot options as the ball moved around to
different players and spots on the court. In-arena work started with the hometown Los Angeles Clippers, and the company also has had its graphics product (called DataFX) used on ESPN’s
SportsCenter,
NBA TV, Fox Sports, and other national outlets.

But while his products focus extensively on ultra-micro analysis, the high-energy Maheswaran takes a very practical, high-level view of what makes his company’s work so potentially valuable.

“When computers understand anything, good things happen for everyone in that ecosystem,” he said while seated at an oversized conference table wedged into limited space in the left prong of the office. “A good example is when computers understood music, you got things like Pandora and Shazam, right? And so the equivalent is when computers understand sports, lots of good things happen. One of the fundamental premises for the technologies that we’re trying to develop is the ability for a computer to understand sports.”

But, Maheswaran notes, technical sophistication in the handling and processing of data is not enough to make for a good consumer product, even when you’re targeting a highly specialized internal audience of NBA teams and their coaching staffs. As good as the information may be, you have to be able to serve it in a way that will make sense to the end users, and won’t force them outside of the way they currently process information.

“So what we try to do is put numbers to words that people already use,” he said. “People already know that a shot is either a good shot or a bad shot, and we have mathematical models that actually quantify the shot—or the shot quality and the shooting ability. We also break down rebounding as not one thing; it’s three things. It’s positioning, attack, and hustle. So, words that coaches already use. But the biggest thing that we do is we use pattern recognition to identify things that happen in a game. So a pick and roll, and reject a screen, and a blitz, an ICE, all these things.”

The biggest hurdle for any external service like Second Spectrum is the potential for distrust of its findings. As longtime NBA coach
Stan Van Gundy (who took over both the head coaching and personnel functions for the Detroit Pistons in 2014) famously railed on at the 2014 Sloan Sports Analytics Conference, many basketball lifers are reluctant to believe
what a computer tells them. Van Gundy’s own hesitation was centered around his perception of the integrity of data input, specifically the qualifications of the people who were assigned to tag plays that fuel the systems of earlier market entrants like Synergy Sports Technology (more on them in a little bit, too).

As Van Gundy argued, there is potential for error when manually identifying and tagging data, especially if the operator is not really sophisticated in understanding the NBA game. Not everything is a straight pick and roll or an isolation or a catch-and-shoot jump shot. There are offensive actions that lead to other actions, which makes it somewhat inaccurate to label them as one specific thing. There are also many defensive tactics that aren’t cut and dry at all, especially when you don’t know the specific context of what the team was asking its players to do. Without knowing more specifics, it can be difficult to identify where a defensive mistake occurred, or why.

For coaches to get value from data, they have to have this kind of exactness. Otherwise, it doesn’t fully conform to their own qualitative ideology on both ends of the court, and can create dissonance when a data report presents information that may counter the coach’s intuition. The ramp-up of this kind of basketball understanding and precision as Maheswaran’s team developed their algorithms was the most crucial piece to building Second Spectrum from an academic idea into a successful commercial business.

“You can do tests against humans and say, ‘Here’s what our computer said, and here’s what a bunch of people said. [What] your stats said.’ And you can go against their staff, and maybe it’s not as good as their staff, but if it’s close, very very close, then you save them a lot of time,” Maheswaran said.

“The hard part about it is this concept of accuracy, both in terms of precision—if I say it’s a pick and roll, is it really a pick and roll?—and
recall—how many of them do I actually catch? So there’s a balance. Because I could say, ‘Every single second of the game is a pick and roll,’ and I’ve gotten all of them, but my accuracy isn’t very good, or I could find the one pick and roll I’m
sure
is a pick and roll and say, ‘that’s a pick and roll,’ and my precision is perfect, but I missed a bunch. So how do you get high [marks] in both those areas?

“It turns out [for] a variety of people, it’s pretty easy to get 80–80. We had an undergrad who was able to get 80 percent precision and 80 percent recall in like three, four days. . . . The question is would that be OK for people who have large numbers [of data points]? And, there’s also bias. [If] you’re getting the 80 easiest ones, so you’re missing all the rejections and the slips [of screens], well, that’s a big deal. So the thing that we have brought to the table is the fact that we understand [these distinctions]. Our algorithms tend to be in the high 90s for [both] precision and recall. So we’re missing very, very few things. We’re basically better than most human beings, if you look at a collection of analysts. We can watch to an almost-human level.”

The result is Second Spectrum’s platform can parse anything from any number of games, and display the information in both digital and video form. The power of their output is staggering.

To give me an example, Maheswaran turned and started fidgeting with a laptop that was feeding a picture onto a large wall-mounted projection screen near the conference table. He tapped into the company’s Eagle system and queued up every pick and roll Clippers point guard Chris Paul had run so far in the 2014–15 season, and requested to see the plays unfold on video from three seconds before the actual screen was set (so we could see how Paul sets up the screens) through one second after the pick (to see what his initial decision would be).

These four-second plays looped continuously, one after another on the screen, and in a matter of a few minutes, we had visually consumed Chris Paul’s entire pick-and-roll repertoire from the current season. Work that would have taken a team’s video coordinator hours to compile a decade ago, now is available in seconds with a few
mouse clicks. Maheswaran said that his system can even assuage the fears of the Van Gundys of the world, because it also can log actions that aren’t the final action of a play. It can essentially track anything you enable it to learn.

“The power of having good algorithms is that it’s like you have a million pairs of eyes watching every single game,” he said. “You can scale. Whenever [you] want to know about the game, it’s as if you have someone who has watched every single second of your opponent’s game and you can get very complete scouting, or every single second of a particular player that you’re trying to scout.

“It’s not that you go back and watch the last three, five games and have a video staff chop it up. You can basically get information about every single moment of the game. Every single pick that led to a post up, that led to a layup. The things that happened—maybe a pick and roll that was stopped, that’s something that you might want information about. Or a pick and roll that was defended well [and] that might’ve led to something else, that led to an iso, that led to a score, and somebody might report, ‘Well, there was an iso,’ but you don’t talk about all the other things that we stuffed.”

So far, Maheswaran’s bet on his and his colleagues’ technological chops—specifically the discipline of spatiotemporal pattern recognition, which he oversimplifies as the science of “moving dots”—is paying significant dividends. With around 30 percent of the NBA as clients, Second Spectrum started adapting its technology for other sports, including professional football and soccer. The group also found a new home quickly after the aforementioned visit, shedding the
U-
shaped office for much bigger space near City Hall, a couple of miles northeast of Staples Center.

While the technology is complicated, Maheswaran and his team have simplified the output to make for an elegant end-user experience. The use of language that basketball people actually use provides staffs with subject comfort as they seek out information that they think will help them make decisions. Knowing that coaches and
their staffs often are less receptive when data is pushed onto them, Second Spectrum’s technology promotes the pulling of only the data that they’re interested in.

“We have not tried to necessarily generate a whole new class of things,” Maheswaran said. “We go to the coaches and say, ‘What is it that you would want to know that you cannot know right now? Or what is it that you want to do that you cannot do right now?’ And we use the fact that a computer understands to get that to them. We don’t come up and say, ‘We’ve got seven new magic metrics that tell you what you should do,’ because coaches really, I think, if given the information, know their teams well, know their constraints well, and will figure out what the right thing is to do.

“The question is: Do you have all the information you need, when you’re making your decision? And one of our things is the most informed make the best decisions, and there is a bottleneck in terms of how well informed you can be based on the technology and the manpower you have. And what we do is just give you basically one hundred times the power of having way more information, or one thousand times the power. I’m not sure quite how to measure this. The other thing we can do is because we have a computer that understands the data, we’ve also done some algorithms that allow the computers to understand the video.

“So here, now, coaches have the initiative to look at numbers,” he added, “[and since] we’ve used the power of the fact that the computer understands both the video and the data, you could essentially ask a question and get the answer both in numbers and in video, instantaneously. So that is a very, very powerful thing.”