This article focuses on the performance of runners in official races. Based on extensive public data from participants of races organized by the Boston Athletic Association, we demonstrate how different pacing profiles can affect the performance in a race. An athlete's pacing profile refers to the running speed at various stages of the race. We aim to provide practical, data-driven advice for professional as well as recreational runners. Our data collection covers 3 years of data made public by the race organizers, and primarily concerns the times at various intermediate points, giving an indication of the speed profile of the individual runner. We consider the 10 km, half marathon, and full marathon, leading to a data set of 120,472 race results. Although these data were not primarily recorded for scientific analysis, we demonstrate that valuable information can be gleaned from these substantial data about the right way to approach a running challenge. In this article, we focus on the role of race distance, gender, age, and the pacing profile. Since age is a crucial but complex determinant of performance, we first model the age effect in a gender- and distance-specific manner. We consider polynomials of high degree and use cross-validation to select models that are both accurate and of sufficient generalizability. After that, we perform clustering of the race profiles to identify the dominant pacing profiles that runners select. Finally, after having compensated for age influences, we apply a descriptive pattern mining approach to select reliable and informative aspects of pacing that most determine an optimal performance. The mining paradigm produces relatively simple and readable patterns, such that both professionals and amateurs can use the results to their benefit.

中文翻译：

---

起搏特性对长距离跑步中表现的影响。

本文着重介绍正式比赛中跑步者的表现。根据波士顿体育协会组织的比赛参与者的大量公共数据，我们演示了不同的起搏配置如何影响比赛的表现。运动员的步调曲线是指比赛各个阶段的跑步速度。我们旨在为职业选手和休闲跑步者提供实用的，以数据为依据的建议。我们的数据收集涵盖了比赛组织者公开的3年数据，并且主要关注各个中间点的时间，从而表明单个跑步者的速度状况。我们考虑了10公里，半程马拉松和全程马拉松，得出120,472个比赛结果的数据集。尽管这些数据并非主要记录用于科学分析，我们证明，可以从这些实质性数据中收集有价值的信息，以了解应对挑战的正确方法。在本文中，我们重点关注种族距离，性别，年龄和起搏配置文件的作用。由于年龄是决定性绩的关键因素，因此我们首先以性别和距离特定的方式来模拟年龄效应。我们考虑高阶多项式，并使用交叉验证来选择既准确又具有通用性的模型。在那之后，我们对种族轮廓进行聚类，以识别跑步者选择的主要节奏轮廓。最后，在补偿了年龄影响后，我们采用描述性模式挖掘方法来选择可靠且信息丰富的起搏方式，这些方面最能决定最佳性能。