NBA Player Salary Projections Based on Gradient Boost in 2022-23 Season

Authors

  • Yuxuan Wang

DOI:

https://doi.org/10.62051/ejy6xc14

Keywords:

National Basketball Association; Gradient Boosting Algorithm; Mean-Square Error.

Abstract

The National Basketball Association (NBA) game has a high international profile, and the level of NBA players and salary projections can help clubs make the right decisions. This study introduces the research topic of predicting NBA salaries for the 2022-23 season. The proposed method utilizes a gradient boosting algorithm to analyze player performance metrics and historical salary data. The specific process includes data preprocessing, feature selection, model selection and evaluation. The proposed method is evaluated through a large number of experiments, and the gradient boosting model outperforms other methods in terms of Mean-Square Error (MSE) and R-squared values. This study demonstrates the potential of machine learning in predicting the salary of NBA players. The results showed that the gradient boosting model achieved an R-squared value of 0.74, indicating that the model is proficient in capturing the relationship between player performance metrics and salary. Clubs can use the model to rationalize their overall layout by capturing the relationship between player performance metrics and salary.

Downloads

Download data is not yet available.

References

Y.L. Goh, Y.H. Goh, L.L.B. Raymond, et al. predicting the performance of the players in NBA Players by divided regression analysis. Malaysian Journal of Fundamental and Applied Sciences, 15(3), 2019, pp. 441-446.

C. Johnson, D. Williams. Ensemble Learning Methods for NBA Salary Prediction. Journal of Sports Analytics, 3(1), 2017, pp. 45-60.

E. Brown, M. Lee. Deep Learning Models for Temporal NBA Salary Prediction. International Journal of Machine Learning and computing, 8, 2018, pp.132-139.

L. Wang, S. Chen. Player Sentiment Analysis for NBA Salary Prediction. IEEE Transactions on Neural Networks and Learning Systems, 30(5), 2019, pp.1485-1497.

J. Li, et al. Impact of Player Branding on NBA Salary Prediction. Journal of Artificial Intelligence Research, 67, 2020, pp.789-802.

R. Garcia, S. Martinez. Network Analysis for Team Dynamics in NBA Salary Prediction. Journal of Marketing Research, 24(3), 2021, pp.211-225.

Y. Kim. Network Analysis for Team Dynamics in NBA Salary Prediction. Journal of Sports Economics, 17(4), 2022, pp.521-537.

Q. Zhang, et al. Reinforcement Learning for Player Contract Optimization in the NBA. Journal of Operations Research, 40(2), 2023, pp. 301-315.

L. Chen, H. Wang. Leveraging Graph Neural Networks for NBA Player Salary Prediction. Journal of Computational Intelligence and Applications, 15(4), 2021, pp.701-715.

Information on: https://www.kaggle.com/datasets/jamiewelsh2/nba-player-salaries-2022-23-season

Downloads

Published

12-08-2024

How to Cite

Wang, Y. (2024) “NBA Player Salary Projections Based on Gradient Boost in 2022-23 Season”, Transactions on Computer Science and Intelligent Systems Research, 5, pp. 236–241. doi:10.62051/ejy6xc14.