How Microsoft Helped ESPN With Its Top 100 All-Time NBA Rankings
When it comes to sports rankings, they could be generated by the old-school barbershop style of getting people in a room to hash out the results via exhausting arguments or with the help of some technology.
For ESPN's All-Time NBA Rankings, which hit the Internet nearly two weeks ago to quite the reaction, the Worldwide Leader in Sports used a mix of both.
As fans flocked to the rankings and continue to weigh in on the results, what many of them don't know is the technological lengths that ESPN went to to create its NBA Top 100, which has none other than Michael Jordan sitting as the greatest of all time.
To help make this happen, ESPN tabbed Microsoft Research for the assist. Microsoft Research specializes in using long-range academic style research to better understand how technology works and where it's going, keying in on the collection of data, aggregating it and how people use it.
The first line of order was for ESPN's esteemed panel of basketball experts to name who they thought were the greatest 150 players in NBA history. From there, the players that came up most were handed to Microsoft Research, which used the names to create its PredictWise Surveys via its customized pairwise comparison engine.
The comparison engine essentially generates matchups, pitting some of the best players of all time against each other — regardless of the eras in which they dominated the league.
Microsoft Research was kind enough to create a username and password for Tech Times, and we were able to see the kinds of cross-generational matchups that came up within a few clicks.
One such matchup had Kareem Abdul-Jabbar up against LeBron James.
Another click generated the King James vs. Kobe Bryant matchup.
Now, Bryant and James are still in the league, but the Mamba's peak years have long passed, and this comparison engine focuses on peak performance years when it generates its matchups. So, in other words: was Kobe's prime greater than LeBron's prime?
"We needed the players to make sense, so the players had to be fairly close to each other in quality, but they had far enough apart that the ballot would then generate meaningful results later on, so they had to really tweak, tweak, tweak, with back-and-forth testing to where they created the unique ballot, which, as far as I know, is unlike any ballot that ever existed," Royce Webb, ESPN's director of content analytics, told us about the early stages of the process and using the comparison engine's matchup generator.
Through ESPN's panel aggressively answering the series of matchups generated, those 150 names were whittled down to 100.
"What we did was we went in and created prior rankings of those 150 names, so that if you're one of our voters and going into our ballot, you don't necessarily want to rank LeBron James vs. some player way down the ballot —Shawn Kemp or somebody," Webb continued. "What you want to do is focus on LeBron James vs. Bill Russell. So, Microsoft helped us create that sort of intelligence in the ballot, which is unseen by the voters. They don't know that that's happening, but it's creating really interesting matchups over and over again. And from those matchups emerged the rankings.
"It has a pretty deep scientific and mathematical basis to it," he added.
In speaking to Microsoft Research economists David Rothschild and Etan Green, this is how they likened the pairwise comparison engine used for ESPN's Top 100 all-time NBA rankings.
"Remember when Mark Zuckerberg — before he came out with Facebook — he had this program called Hot or Not?" Green told Tech Times. "Essentially, what we're doing is the same thing, but without the vulgarity, and we think put to a slightly more interesting purpose and with a little bit more complexity on the back end."
So, who fell under Jordan to make the top five of ESPN's all-time Top 100 NBA rankings?
MJ was followed by the league's all-time leading scorer in Kareem Abdul-Jabbar and James, who many people felt was ranked too high. Rounding out the top five was Magic Johnson and Wilt Chamberlain. Fair enough, right?
Well, out of those first five names, the one that fans seemed to take issue with the most was James being so high, with seemingly much of his career still not spoken for.
"We make no presumptions that the rankings are correct in any objective sense," Rothschild said. "Our only objective is that they reflect the view of the people who voted. The debate of where LeBron should be ranked is an interesting one, and it's one that's generating lot of value for ESPN."
Green and Rothschild additionally told us that there are probably ways of getting to the same ranking through fewer comparisons, but through this random but educated manner of comparing players, they believe their ranking was not only more efficient, but also more enjoyable.
While there will always be gripes when it comes to player rankings, perhaps Webb says it best.
"Hey ... you've got to fall somewhere on the list."
Fans can begin to see ESPN's all-time NBA Top 100 rankings here.