Fig 1.
NBA game outcome prediction model construction and application flowchart.
Fig 2.
Framework diagram of the SHAP algorithm.
Table 1.
Definition of selected technical game performance-related variables.
Fig 3.
Heatmap of NBA game technical statistics data.
The color of the heatmap indicates the correlation between two features: darker colors represent stronger positive correlations, while lighter colors represent stronger negative correlations. The numerical values represent the correlation coefficients between corresponding features. The asterisks reflect the significance levels of the correlation coefficients: no asterisk denotes p > 0.05, one asterisk denotes 0.01 < p < 0.05, two asterisks denote 0.001 < p < 0.01, and three asterisks denote p < 0.001.
Fig 4.
Exploratory scatter plots of technical statistic relationships from full game.
Table 2.
List of feature data for the sample.
Table 3.
Logistic regression analysis results of key performance variables during the first two quarters.
Table 4.
Logistic regression analysis results of key performance variables during the first three quarters.
Table 5.
Logistic regression analysis results of key performance variables during the full game.
Table 6.
Confusion matrix of classification results.
Fig 5.
Comparative chart of performance evaluation metrics for NBA game outcome prediction models.
(a) first two quarters period, (b) first three quarters period, (c) full game period. SVM = Support Vector Machines; KNN = K-Nearest Neighbors.
Table 7.
Comparative results of performance evaluation metrics for NBA game outcome prediction models (first two quarters period).
Table 8.
Comparative results of performance evaluation metrics for NBA game outcome prediction models (first three quarters period).
Table 9.
Comparative results of performance evaluation metrics for NBA Game outcome prediction models (full game period).
Fig 6.
Summary chart of SHAP feature importance at different time of the game.
(a) first two quarters period, (b) first three quarters period, (c) full game period.
Table 10.
Comparison of SHAP feature importance at different time of the game.
Fig 7.
Interpretation of SHAP force plot: analysis of performance in the first two quarters of G2 game.
The base value represents the average predicted probability of win or loss for the sample set of games, with red areas indicating that the feature has a positive effect on the prediction outcome, and blue areas indicating a negative effect. The length of the color bars reflects the magnitude of the impact, with longer bars signifying a greater influence of that particular feature on the prediction result. Features and their sample values are indicated below the color bars. Footnotes for Figs 8 and 9 are identical to that of Fig 7.
Fig 8.
Interpretation of SHAP force plot: analysis of performance in the first three quarters of G2 game.
Fig 9.
Interpretation of SHAP force plot: analysis of performance in the full G2 game.
Table 11.
Impact of important variables and other variables on game outcome during the first two quarters of G2 game.
Table 12.
Impact of important variables and other variables on game outcome during the first three quarters of G2 game.
Table 13.
Impact of important variables and other variables on game outcome during the full G2 game.