Alagappan’s discoveries won the award for best evolution in sport this spring at the annual conference MIT Sloan Sports Analytics Conference.
Whenever sport and numbers meet, the Silver ball A question inevitably arises: is it possible to use large datasets to find undervalued actors? Alagappan thinks so.
He isolated the 40 players in the “goal rebounder” section who best embodied this group. At the top were the stars to be expected: Carmelo Anthony and Amare Stoudemire of the New York Knicks, as well as Nowitzki and Paul Gasol of the Los Angeles Lakers. But lesser-known players like the Memphis Grizzlies ‘Marreese Speights and the Lakers’ Devin Ebanks produced statistically similar results per minute. Better yet, where Anthony’s average salary is around $ 18.5 million a year, the Lakers pay the Ebanks around $ 740,000.
Another inevitable question: Could Ayasdi’s software have predicted the success of Knicks rookie Jeremy Lin? Alagappan concedes that Lin’s college statistics wouldn’t have suggested or predicted Linsanity, but he created a web of similars to identify players most similar to Lin in college. Three names emerged from the 3,400 analyzed: DeMarcus Cousins, whom the Sacramento Kings picked fifth overall in the 2010 NBA Draft; Alec Burks, chosen 12th in 2011 by Utah Jazz; and Nik Raivio, a University of Portland goaltender who currently plays ball in Kaposvar, Hungary.
Lesson? For teams that adhere to this new classification of players, the next Jeremy Lin could be in Hungary, pending your call.
Photo: Dallas Mavericks Dirk Nowitzki (41) and Jason Terry (31) defend Dwyane Wade of the Miami Heat in the second half of Game 2 of the 2011 NBA Finals. Photo: David J. Phillip / Associated Press