Posts

Predicting the 2019 All-NBA teams with machine learning

Image
There is a summary at the bottom if you want to skip to the results. Introduction Last year, media members unanimously selected LeBron James to the All-NBA first team, giving him a record 12 All-NBA first team selections. However, given the Lakers recent struggles and LeBron's absence earlier in the season, LeBron might miss not only the first team but also the second team. This would mark the first time since his rookie year he misses both of the top two teams. With two MVP-caliber forwards in Giannis Antetokounmpo and Paul George and two more superstar forwards on top teams in Kevin Durant and Kawhi Leonard, LeBron presents almost no case to earn a spot on the first or second team. Barring a scorching hot run by the Lakers to end the year, LeBron will have a significantly worse team record and worse stats than these 4 players. For the second year in a row, voters unanimously placed James Harden on the first team. This streak seems certain to extend given Harden's un

Using machine learning to predict the 2019 MVP: All-Star break predictions

Image
This is the second installment of predicting the 2019 MVP. To see the first post, click here . Summary Introduction About a month ago, our models predicted Giannis Antetokounmpo will win the 2019 NBA MVP. Each model - and the average of the four models - crowned Giannis as MVP with a decent margin above Harden and the rest of the pack.  However, since this date, several candidates have made strong runs. The night after I collected the data to make the post, James Harden posted a 57-point game against the Grizzlies. He then followed it up with a 58-point game two days later, and a 61-point game one week later. In the 15 games since the previous post, Harden has been averaging 42.7 points along with 7.9 rebounds and 5 assists. Similarly, Paul George's recent hot streak has vaulted him from 6th in NBA.com's MVP ladder up to 3rd. Though many view the MVP race as a close 2-man ran between Giannis and Harden, Paul George forced his way into this discussion with his re

Using machine learning to predict the 2019 MVP: mid-season predictions

Image
Summary Introduction With James Harden's recent stretch, the Nuggets' success despite their injuries, and the Bucks maintaining the second seed in the NBA, Harden, Jokic, and Giannis all have strong cases for MVP this year. Though Harden hasn't had the same team success as Jokic and Giannis, he's been averaging an absurd 34.2 PPG - almost 5 PPG more than second place Steph Curry. On the other hand, Jokic has been leading an injury-riddled Nuggets team to the first seed in the West. Along the way, he's had numerous incredible all-around performances, such as Monday's 40/10/8 game against the Trail Blazers. Jokic averages the 9th most assists per game in the league, an unprecedented figure for a center. Meanwhile, Giannis has been posting a hyper-efficient 27/12/6 while leading the Bucks to the NBA's second best record. In addition to these players, Curry and Kawhi have legitimate arguments for MVP, as they've played very well for the best teams in