Sipply
每日摘要

研究约 1 分钟阅读最近更新

新模型使用分位数回归估计运动员的到达时间New model estimates sports players' time-to-arrival using quantile regression

1 家来源 · 1 篇报道 — 来源较集中（请仔细核对）

以下内容为 AI 自动翻译，英文原文附后供参考。

摘要

最近的一项研究开发了一种新方法，通过对跟踪数据进行条件分位数回归来估计运动员在各种运动中的到达时间（TTA）。研究人员在2022年国际足联世界杯的跟踪数据上训练了一个多层感知器模型，证明其显著优于传统的基于物理的模型。这一进展表明，该方法可以适用于多种运动，增强对运动员动作和策略的理解。

A recent study has developed a novel method for estimating the time-to-arrival (TTA) of players in various sports, utilizing conditional quantile regression on tracking data. The researchers trained a multilayer perceptron model on tracking data from the FIFA World Cup 2022, demonstrating that it significantly outperforms traditional physics-based models. This advancement suggests that the approach could be applicable across a range of sports, enhancing the understanding of player movements and strategies.

要点

  1. 新模型使用分位数回归来改善运动员的TTA预测。

    The new model uses quantile regression to improve TTA predictions for sports players.

  2. 在2022年国际足联世界杯数据上的训练显示该模型相较于传统方法的有效性。

    Training on FIFA World Cup 2022 data shows the model's effectiveness over traditional methods.

  3. 该方法在足球以外的多种运动中具有潜在应用。

    The approach has potential applications in various sports beyond soccer.

为何重要

这项研究代表了体育分析的重要进展，为团队和教练提供了更好的工具来分析运动员的动作和策略。

This research represents a significant step forward in sports analytics, providing teams and coaches with better tools to analyze player movements and strategies.

按谁的角度看

产品经理

对于产品经理而言，这项研究强调了将先进的机器学习技术整合到体育分析产品中的重要性，以增强决策能力。

For product managers, this study highlights the importance of integrating advanced machine learning techniques into sports analytics products to enhance decision-making capabilities.

开发者

开发人员可以利用这项研究创建更复杂的模型，改善体育中的预测分析，可能导致新的应用和功能。

Developers can leverage this research to create more sophisticated models that improve predictive analytics in sports, potentially leading to new applications and features.

学生与求职者

数据科学和体育分析领域的学生和求职者可以从这项研究中获得见解，展示机器学习在现实场景中的应用及其创新职业路径的潜力。

Students and job-seekers in data science and sports analytics can gain insights from this study, showcasing the application of machine learning in real-world scenarios and the potential for innovative career paths.

覆盖来源

来源标题与摘录保留原文，以便核对与追溯。

  • arXiv cs.AI

    Learning Human Sports Motion Feasibility via Quantile Regression on Tracking Data

    The study introduces a method to estimate the time-to-arrival (TTA) for players in sports using conditional quantile regression on tracking data. By training a multilayer perceptron on FIFA World Cup 2022 tracking data, the model outperforms traditional physics-based models and shows potential for application across different sports.