條件熵是信息理論中的一個重要概念，用於量化給定一個隨機變數的值的條件下，另一個變量的不確定性。本論文利用條件熵以及條件熵下降的概念對 NBA 球員資料做類別資料分析，試著找出影響平均得分最為重要的變數，透過結合變數從條件熵獲得更多的訊息再加以分析，找出的關鍵變數為球權使用率及籃板，並針對 11 位現今 NBA的知名球員、特定球員 Dwight Howard 及 Carmelo Anthony 做分析，找出影響知名球員的變數為球員本身，Dwight Howard 最關鍵的變數為真實命中率、籃板及年齡，Carmelo Anthony 則是真實命中率，最後再將結果與隨機森林方法的重要變數比較。

Conditional entropy is a crucial concept in information theory, utilized to measure the uncertainty of one variable given the value of another random variable. This study applies the concept of conditional entropy and examines conditional entropy drops to conduct a categorical data analysis on NBA player data, aiming to identify the most influential variables impacting average scores. By incorporating additional variables to extract more information from conditional entropy, we deepen our analysis. The key variables identified include usg_pct and reb. Our analysis focuses on eleven prominent contemporary NBA players, with specific attention given to Dwight Howard and Carmelo Anthony. The variable found to influence prominent players is player_name. For Dwight Howard, the critical variables found to influence his performance are ts_pct, reb, and age. Meanwhile, for Carmelo Anthony, the defining variable is ts_pct. Finally, we compare our results with the important variables determined by the Random Forest method.

Breiman, L. (2001). Random forests. Machine learning, 45:5–32.
Cao, C. (2012). Sports data mining technology used in basketball outcome prediction.
Chen, T.-L., Chou, E. P., and Fushing, H. (2021). Categorical nature of major factor selection via information theoretic measurements. Entropy, 23(12):1684.
Cirtautas, J. (2022). Nba players. https://www.kaggle.com/datasets/justinas nba-players-data.
Cortes, C. and Vapnik, V. (1995). Support-vector networks. Machine learning, 20:273–297.
Duda, R. O., Hart, P. E., et al. (1973). Pattern classification and scene analysis, volume 3.Wiley New York.
Fisher, R. A. (1936). The use of multiple measurements in taxonomic problems. Annals of eugenics, 7(2):179–188.
Guyon, I. and Elisseeff, A. (2003). An introduction to variable and feature selection. Journal of machine learning research, 3(Mar):1157–1182.
Guyon, I., Weston, J., Barnhill, S., and Vapnik, V. (2002). Gene selection for cancer classification using support vector machines. Machine learning, 46:389–422.
Hlaváčková-Schindler, K., Paluš, M., Vejmelka, M., and Bhattacharya, J. (2007). Causality detection based on information-theoretic approaches in time series analysis. Physics Reports, 441(1):1–46.
Hu, Q., Yu, D., Liu, J., and Wu, C. (2008). Neighborhood rough set based heterogeneous feature subset selection. Information sciences, 178(18):3577–3594.
Kira, K. and Rendell, L. A. (1992). A practical approach to feature selection. In Machine learning proceedings 1992, pages 249–256. Elsevier.
Kononenko, I. et al. (1994). Estimating attributes: Analysis and extensions of relief. In ECML, volume 94, pages 171–182. Citeseer.
LeCun, Y., Bengio, Y., and Hinton, G. (2015). Deep learning. nature, 521(7553):436–444.
Liaw, A. and Wiener, M. (2002). Classification and regression by randomforest. R News, 2(3):18–22.
Loeffelholz, B., Bednar, E., and Bauer, K. W. (2009). Predicting nba games using neural networks. Journal of Quantitative Analysis in Sports, 5(1).
Meyer, P. E. (2022). infotheo: Information-Theoretic Measures. R package version 1.2.0.1.
Oughali, M. S., Bahloul, M., and El Rahman, S. A. (2019). Analysis of nba players and shot prediction using random forest and xgboost models. In 2019 International Conference on Computer and Information Sciences (ICCIS), pages 1–5. IEEE.
Pawlak, Z. (1982). Rough sets. International journal of computer & information sciences, 11:341–356.
Peng, H., Long, F., and Ding, C. (2005). Feature selection based on mutual information criteria of max-dependency, max-relevance, and min-redundancy. IEEE Transactions on pattern analysis and machine intelligence, 27(8):1226–1238.
Zou, H. and Hastie, T. (2005). Regularization and variable selection via the elastic net. Journal of the royal statistical society: series B (statistical methodology), 67(2):301–320.