School of IT, Deakin University, Melbourne, Australia.
Research Centre for Fluid and Complex Systems, Coventry University, Coventry, United Kingdom.
PLoS One. 2024 Oct 30;19(10):e0312278. doi: 10.1371/journal.pone.0312278. eCollection 2024.
In association football, predicting the likelihood and outcome of a shot at a goal is useful but challenging. Expected goal (xG) models can be used in a variety of ways including evaluating performance and designing offensive strategies. This study proposed a novel framework that uses the events preceding a shot, to improve the accuracy of the expected goals (xG) metric. A combination of previously explored and unexplored temporal features is utilized in the proposed framework. The new features include; "advancement factor", and "player position column". A random forest model was used, which performed better than published single-event-based models in the literature. Results further demonstrated a significant improvement in model performance with the inclusion of preceding event information. The proposed framework and model enable the discovery of event sequences that improve xG, which include; opportunities built up from the sides of the 18-yard box, shots attempted from in front of the goal within the opposition's 18-yard box, and shots from successful passes to the far post.
在足球中，预测射门进球的可能性和结果是很有用的，但也具有挑战性。预期进球 (xG) 模型可以通过多种方式使用，包括评估表现和设计进攻策略。本研究提出了一种新的框架，该框架使用射门前的事件来提高预期进球 (xG) 指标的准确性。所提出的框架中利用了之前探索和未探索的时间特征的组合。新特征包括“推进因素”和“球员位置列”。使用随机森林模型，该模型的性能优于文献中已发表的基于单事件的模型。结果进一步表明，通过包含之前的事件信息，模型的性能得到了显著提高。所提出的框架和模型能够发现提高 xG 的事件序列，其中包括：从 18 码框的两侧建立的机会、在对方 18 码框内从球门正面尝试的射门、以及从成功传至远门柱的射门。
