Proposal for a U.S. College Basketball Player Recommendation System for the B-League

In the B-League, Japan professional basketball league, foreign players account for a large percentage of scoring and are core. Therefore, strategy scouting talented is essential teams. However, team managers can not survey all because there many leagues huge number players. most done through agents, so intermediary costs significant. We propose an efficient system to find from NCAA (National Collegiate Athletic Association) where in B-League came from. focus on following topics: (1) Classify playing styles using k-means. (2) Estimate players’ style classification model. (3) lineups regression. (4) available budget based age distribution. (5) Simulation Chiba Jets Funabashi, which team. verified accuracy those play-by-play boxscore data 2015-16 2021-22 2005-06 seasons. As result, although some issues have be resolved, we demonstrated its potential contribute efficiency player scouting.