The application of machine learning and deep learning in sport: predicting NBA players’ performance and popularity

Abstract

Basketball is known for the vast amount of data collected for each player, team, game, and season. As a result, basketball is an ideal domain to work on different data analysis techniques to gain useful insights. In this study, we continued our previous study published in 2020 Computational Collective Intelligence (12th International Conference, ICCCI 2020, Da Nang, Vietnam, November 30 – December 3, 2020, Proceedings) reviewing some important factors to predict players’ future performance and being selected in an All-Star game, one of the most prestigious events, of National Basket Association league. Besides traditional Machine Learning, Deep Learning is also applied in this study for prediction purpose. However, compared to traditional Machine Learning, Deep Learning’s performance is not as good for our dataset. It is understandable when our data are relatively small and structured with a few predictor variables which limited Deep Learning’s ability to deal with a vast amount of Big Data. Our final results, through both Regression and Classification Analysis, indicated that scoring is the most important factor from the primary players for any team and also basketball fan’s favourable style.

Cite this work

No public copy is stored for this record, so only the metadata is cited.

Stored only when both papers are in the corpus — 72 citations exist upstream.

Papers that cite the same references — the relational fallback while embeddings are still backfilling.