Centre for Sport Research, Deakin University, Geelong, Australia.
School of Information Technology, Deakin University, Geelong, Australia.
J Sports Sci. 2020 Mar;38(6):676-681. doi: 10.1080/02640414.2020.1724044. Epub 2020 Feb 7.
The aim of this study was to assess if tactical and technical performance indicators (PIs) could be used in combination to model match outcomes in Australian Football (AF). A database of 101 technical PIs and 14 tactical PIs from every match in the 2009-2016 Australian Football League (AFL) seasons was merged. Two outcome measures Win-loss and Score margin were used as dependent variables. The top 45 ranked technical and tactical PIs from a feature selection process were used to model match outcome using decision tree and Generalised Linear Models (GLMs). Of the top 45 selected features, this included seven tactical PIs. The Win-loss-based Decision tree model achieved a classification accuracy of 89.0% and GLM 93.2%. A Score margin-based GLM achieved a root mean squared error (RMSE) of 6.9 points. A combined approach to the classification of match outcomes provided no improvement in model accuracy compared with previous literature. However, this study has established the relative importance of technical and tactical measures of performance in relation to successful team performance in AF.
本研究旨在评估战术和技术表现指标（PIs）是否可以结合使用，以预测澳大利亚足球（AF）比赛的结果。将 2009-2016 年澳大利亚足球联赛（AFL）赛季每场比赛的 101 项技术 PIs 和 14 项战术 PIs 的数据库合并。将胜负和得分差距这两个结果衡量指标作为因变量。使用特征选择过程中排名前 45 的技术和战术 PIs，通过决策树和广义线性模型（GLM）来模拟比赛结果。在这 45 个精选特征中，包括 7 个战术 PIs。基于胜负的决策树模型的分类准确率为 89.0%，GLM 为 93.2%。基于得分差距的 GLM 的均方根误差（RMSE）为 6.9 分。与之前的文献相比，分类比赛结果的综合方法并没有提高模型的准确性。然而，本研究已经确定了技术和战术表现指标在与 AF 中成功团队表现相关方面的相对重要性。
