engleski

Game-to-Game Prediction of NBA Players’ Points in Relation to Their Season Average

NBA attracts a great deal of attention among sports analysts and sportsbooks regarding the prediction of various outcomes of each game, together with the parameters which affect them. Performance of NBA players is influenced by many unknown and random factors, such as players' psychological condition, social life and injuries. The stated factors hinder game-to-game predictions of players' performance in relation to the expectations set by their past performances. In this paper we leverage the publicly available statistics to create a dataset pertaining to the performance of a single player during a single season. A comparison between points that a player has scored and his current season average was done in order to classify the player's performance as `over' or `under'. Using various statistical data concerning previous games of the season, a binary classifier was trained in order to distinguish between those categories for future games. The classifier performed with an accuracy score of 56.7%. Since sportsbooks tend to give 50/50 odds of a player going `over' or `under' in relation to their season points per game, these results represent an improvement of 6.7%. Although top features are predominated by offensive statistics (e.g. how many minutes the player plays, how many shots he takes and how strong the offense of his team is), a newly generated feature, which represents tiredness of a player, has shown to be among top 15 informative features.

data analysis, feature extraction, pattern classification, sport, statistical analysis, game-to-game prediction, statistical data, binary classifier, season average, NBA players points

nije evidentirano