Measuring Attack Vectors of Ball-Handlers

As a point guard growing up, I found that driving with my dominant shooting hand would typically put my shooting hand away from the basket. And being undersized at the position (5’4″, 95 pound Sophomore) made life more difficult to shoot off the dribble. Instead, I developed my non-dominant hand, which gave me two options…

Identifying Player Possession in Spatio-Temporal Data

In a previous post, we took a look into some spatio-temporal data obtained through SportVU technology for the NBA and identified how to use that data to perform basic tasks such as building convex hulls to illustrate offense and defense coverage on a court; as well as provide basic Python code for the reader to…

NBA Tracking Using Python: Warriors vs. Grizzlies

With the Golden State Warriors and Memphis Grizzlies are set to square off for the second time this season tonight, we take an extended look at the most recent 119 – 69 Warrior win over the Grizzlies on November 2nd. We do this by looking at two consecutive possessions that resulted in a Warriors basket and a…

Building NBA Defenses Using the Convex Hull

When a basketball team employs a zone-type of defense, they are attempting to remove a specific element from the opposing team’s arsenal. For example, the 2-3 zone defense attempts to pack the lane by placing a strong defensive player in the center of the lane; a basket defender, if you will. This type of defense…

NBA Data Science: Breaking Down NBA Data

Recently, the Oklahoma City Thunder and the San Antonio Spurs played to a frenetic 112 – 106 OKC win on October 28th. It was one heck of a statement to open the year for the NBA as the Thunder returned to the court as a complete, healthy unit; the first time since February of last…