Kate Tiedemann College of Business, University of South Florida St. Petersburg , St. Petersburg, Florida.
Big Data. 2018 Jun;6(2):96-112. doi: 10.1089/big.2017.0054. Epub 2018 Jun 8.
This article proposes a novel approach, called data snapshots, to generate real-time probabilities of winning for National Basketball Association (NBA) teams while games are being played. The approach takes a snapshot from a live game, identifies historical games that have the same snapshot, and uses the outcomes of these games to calculate the winning probabilities of the teams in this game as the game is underway. Using data obtained from 20 seasons worth of NBA games, we build three models and compare their accuracies to a baseline accuracy. In Model 1, each snapshot includes the point difference between the home and away teams at a given second of the game. In Model 2, each snapshot includes the net team strength in addition to the point difference at a given second. In Model 3, each snapshot includes the rate of score change in addition to the point difference at a given second. The results show that all models perform better than the baseline accuracy, with Model 1 being the best model.
本文提出了一种新方法，称为数据快照，用于在比赛进行时为美国职业篮球联赛（NBA）球队生成实时获胜概率。该方法从实时比赛中获取一个快照，识别出具有相同快照的历史比赛，并使用这些比赛的结果来计算比赛中球队的获胜概率。使用从 20 个 NBA 赛季中获得的数据，我们构建了三个模型，并将它们的准确性与基准准确性进行了比较。在模型 1 中，每个快照包括比赛中给定时刻主场和客场球队之间的比分差距。在模型 2 中，每个快照包括净团队实力以及比赛中给定时刻的比分差距。在模型 3 中，每个快照包括比分变化率以及比赛中给定时刻的比分差距。结果表明，所有模型的表现都优于基准准确性，其中模型 1 是最佳模型。
