Share your ideas for the JMP Scripting Unsession at Discovery Summit by September 17th. We hope to see you there!
Choose Language Hide Translation Bar

Predicting a Player's NBA Success Using Collegiate Statistics.pptx


Often, many players entering the NBA as elite draft prospects underperform and fail to meet expectations. Multiple general managers, coaches, and scouts may be quick to place blame on the players, but perhaps there is a lack of data evaluation by team personnel. This poster contains observations and variables from five different data sources, to create a comprehensive data set comprising collegiate players’ statistics and physical attributes. Logistic regression is used on this data set to examine and predict the probability of a player remaining in the NBA four years after being drafted. Those models are also used to predict the probability of a player becoming an All-Star concluding his fourth year post-NBA draft. Examining a NBA player’s performance by year four is imperative considering the average NBA career lasts only 4.8 years. Finally, this poster also attempts to predict a college player’s NBA efficiency rating four years after being drafted in the NBA. Currently this data set contains 25 variables and 391 observations culled from the draft classes between 2003 and 2011. The models created from this poster can add guidance and assist teams with their decision making when choosing a collegiate player to draft.


Article Tags