Hybrid Basketball Game Outcome Prediction Model by Integrating Data Mining Methods for the National Basketball Association

Abstract

The sports market has grown rapidly over the last several decades. Sports outcomes prediction is an attractive sports analytic challenge as it provides useful information for operations in the sports market. In this study, a hybrid basketball game outcomes prediction scheme is developed for predicting the final score of the National Basketball Association (NBA) games by integrating five data mining techniques, including extreme learning machine, multivariate adaptive regression splines, k-nearest neighbors, eXtreme gradient boosting (XGBoost), and stochastic gradient boosting. Designed features are generated by merging different game-lags information from fundamental basketball statistics and used in the proposed scheme. This study collected data from all the games of the NBA 2018–2019 seasons. There are 30 teams in the NBA and each team play 82 games per season. A total of 2460 NBA game data points were collected. Empirical results illustrated that the proposed hybrid basketball game prediction scheme achieves high prediction performance and identifies suitable game-lag information and relevant game features (statistics). Our findings suggested that a two-stage XGBoost model using four pieces of game-lags information achieves the best prediction performance among all competing models. The six designed features, including averaged defensive rebounds, averaged two-point field goal percentage, averaged free throw percentage, averaged offensive rebounds, averaged assists, and averaged three-point field goal attempts, from four game-lags have a greater effect on the prediction of final scores of NBA games than other game-lags. The findings of this study provide relevant insights and guidance for other team or individual sports outcomes prediction research.

Improving Sports Outcome Prediction Process Using Integrating Adaptive Weighted Features and Machine Learning Techniques

“…Therefore, sports outcome prediction became an attractive topic for researchers in different sports domains [10][11][12]. Among different sports, basketball games outcome prediction or forecasting is the most popular topic for researchers [8,9] since National Basketball Association (NBA) is the most welcoming sports league worldwide [13][14][15][16][17][18][19][20][21][22][23][24]. The existing basketball game outcome prediction can be classified in two primary directions: win/lose (W/L) prediction and game score prediction.…”

“…Predicting the future game's W/L is an essential issue for team staff, participants, and fans since W/L is the simplest way to determine the result of a team's performance [13][14][15][16][17][18][19]. However, for technical analyst, betting bookers, and commentators, game score prediction provide more detailed information for stakeholders aforementioned [20][21][22][23][24]. This study proposed an improved sports outcome prediction process by integrating machine learning algorithms for NBA game score prediction.…”

“…Technical analysis assumes that future incidents are correlated to some historical patterns. Moving average (MA) is the mathematical expression of historical data sets defined to describe specific characteristics of presumed hidden rules and is a valuable technical indicator for feature engineering [24,27]. Adaptive weighting (AW) is a promising method to improve the prediction model's performance and applied in various areas [28][29][30].…”

“…Machine learning algorithms have been successfully used to build effective prediction models for different applications in the various area [35][36][37][38][39][40][41]. There is relatively fewer research applying machine learning methods for NBA game outcomes prediction and NBA game final score prediction [16][17][18][19][20][21][22][23][24]. Therefore, five machine learning methods, including classification and regression trees (CART) [42][43][44][45][46][47][48][49], random forest (RF) [50][51][52][53][54][55][56][57][58][59][60], stochastic gradient boosting (SGB) [24,45,52,[61][62][63][64][65][66][67], eXtreme gradient boosting (XGBoost) [24,[68]…”

“…There is relatively fewer research applying machine learning methods for NBA game outcomes prediction and NBA game final score prediction [16][17][18][19][20][21][22][23][24]. Therefore, five machine learning methods, including classification and regression trees (CART) [42][43][44][45][46][47][48][49], random forest (RF) [50][51][52][53][54][55][56][57][58][59][60], stochastic gradient boosting (SGB) [24,45,52,[61][62][63][64][65][66][67], eXtreme gradient boosting (XGBoost) [24,[68][69][70][71][72][73], and extreme learning machine (ELM) [24,[73][74]…”