Anomaly clue localization of multi-dimensional derived measure is vitally important for the reliability of online video services. In this paper, we propose RobustSpot, an end-to-end framework for localizing the clues to anomalous multi-dimensional derived measures. RobustSpot integrates two novel indicators, i.e., “Anomaly Degree” and “Contribution Ability”, with a simple yet effective method, weighted association rule mining (WARM), to automatically mine the hidden relationships across data dimensions for localizing the most likely clues to the root cause. Using 135 real-world cases collected from a top-tier global online video service provider $H$ with 170+ million monthly active users, we demonstrate that RobustSpot achieves high accuracy (Top-5 accuracy of 98%), significantly outperforming state-of-the-art methods. The average localization time of RobustSpot is 1.83s, which is satisfying in our scenario. We have open-sourced the implementation of RobustSpot as well as the data used in the evaluation experiments.

中文翻译：

---

在线视频服务多维导出度量的稳健异常线索定位

多维导出度量的异常线索定位对于在线视频服务的可靠性至关重要。在本文中，我们提出了 RobustSpot，这是一个端到端的框架，用于将线索定位到异常的多维派生度量。RobustSpot 整合了“异常度”和“贡献能力”两个新颖的指标，通过一种简单而有效的方法，加权关联规则挖掘（WARM），自动挖掘跨数据维度的隐藏关系，以定位最有可能的线索到根本原因。使用从全球顶级在线视频服务提供商收集的 135 个真实案例$H$每月有 170 多万活跃用户，我们证明 RobustSpot 实现了高精度（Top-5 准确率为 98%），明显优于最先进的方法。RobustSpot 的平均定位时间为 1.83 秒，这在我们的场景中是令人满意的。我们开源了 RobustSpot 的实施以及评估实验中使用的数据。