Skip to content
  • Twitter
  • GitHub
  • Home page
  • About
  • Data and Python code

About Me

I’m a college freshman and lifelong Celtics fan. I’ve been interested in statistics for a long time, and am starting Dribble Analytics to explore my interest in basketball analytics while learning Python and data science. To read more about the blog and my story, check out the “About” page.

Contact me at: the name of this blog [at] gmail [dot] com

Dribble Analytics

open-source basketball analytics

July 8, 2019July 18, 2019

Generating stats-based historical comparisons for the draft lottery

As soon as a player is drafted, we compare them to historical stars based on their play styles. Let’s use their stats and some similarity metrics to create more concrete comparisons.

Posted in Similarity, The Draft. Leave a comment
June 20, 2019June 20, 2019

Predicting the best scorers in the 2019 draft with machine learning

With the 2019 draft unclear looking inconsistent after the top 3, let’s try to predict the best scorers in the draft with machine learning. Who will be the hidden gem who could shine as a scorer?

Posted in Regression, The Draft. Leave a comment
May 3, 2019May 2, 2019

A new approach to analyzing the value of tanking: Markov chains

Many claim tanking is worth it because players drafted earlier have a higher chance of being good. However, the draft is random. Let’s use Markov chains (a random process) to analyze if tanking is worth it.

Posted in The Draft. 2 Comments
April 23, 2019April 26, 2019

Defining NBA players by role with k-means clustering

In the modern NBA, players serve roles that are much different from their expected position. Let’s use k-means clustering to group the NBA into 12 roles.

Posted in Clustering. Leave a comment
April 12, 2019April 11, 2019

Using machine learning to predict the 2019 MVP and All-NBA teams: end of season predictions

Over the past few months, we’ve been using machine learning to predict the MVP and All-NBA teams. Now that the season is done, let’s update these predictions and predict our final MVP and All-NBA teams.

Posted in Classification, NBA Awards, Regression. Leave a comment
March 1, 2019October 12, 2019

Predicting the 2019 All-NBA teams with machine learning

Now that we’re over halfway done with the regular season, the All-NBA picture is clearing up. By creating accurate models which examine the factors that lead each historical All-Star and top player to make (or miss) an All-NBA team, we can predict each player on all 3 All-NBA teams.

Posted in Classification, NBA Awards. 2 Comments
February 19, 2019June 17, 2019

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

This is the second installment of predicting the 2019 MVP with machine learning. Since the first installment, James Harden has strengthened his MVP case, while Giannis Antetokounmpo has continued to lead the NBA-leading Bucks. Meanwhile, Paul George’s hot streak has shaken up the rest of the pack.

Posted in NBA Awards, Regression. Leave a comment
January 16, 2019June 17, 2019

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

With the halfway point in the year passing, the MVP discussion is heating up. James Harden and Giannis Antetokounmpo find themselves in a tight 2-man race for MVP. Let’s see who should win based off historical precedent for MVP vote share.

Posted in NBA Awards, Regression. Leave a comment
January 3, 2019April 7, 2019

Visualizing how much the top 10 NBA players would earn without max contracts

The CBA creates a price ceiling for the top NBA players. Though there are lots of max contract players who are being overpaid, the league’s best remain underpaid. Let’s take a simple statistical look to adjust the top 10 players’ salary to the rest of the league.

Posted in Salary. Leave a comment
October 2, 2018April 7, 2019

Using machine learning to predict hall of famers and all stars from the 2017 draft

Out of the first round in every draft class, on average, only 1 player makes the hall of fame, and about 2-3 players make an All-Star game at some point in their career. Let’s use classification models to see who those players are from the 2017 draft class.

Posted in Classification, The Draft. Leave a comment

Posts navigation

Older posts
Newer posts
Proudly powered by WordPress | Theme: Coherent by WordPress.com. | Dribble Analytics