The NBA is widely considered to be the best basketball league in the world, and has grown over its seven-decade existence into a multibillion-dollar industry. Central to this industry is the problem of roster construction, as team performance depends critically on selecting productive players for all 15 roster spots.

In this project, we aim to perform a novel analysis of NBA statistics, salary, and transaction data in order to determine whether or not a given player will be in the NBA in the next season (i.e., we predict NBA player retention). The resulting model has the potential to aid in the selection of players toward the end of the roster, which has long been one of the most challenging aspects of team construction.