At eBay, there are thousands of product health metrics for different domain teams to monitor. We built a two-phase alerting system to notify users with actionable alerts based on anomaly detection and alert retrieval. In the first phase, we developed an efficient anomaly detection algorithm, called Moving Metric Detector (MMD), to identify potential alerts among metrics with distribution agnostic criteria. In the second alert retrieval phase, we built additional logic with feedbacks to select valid actionable alerts with point-wise ranking model and business rules. Compared with other trend and seasonality decomposition methods, our decomposer is faster and better to detect anomalies in unsupervised cases. Our two-phase approach dramatically improves alert precision and avoids alert spamming in eBay production.
翻译:在eBay上,有数千个产品健康计量标准供不同领域小组监测。我们建立了一个两阶段警报系统,向用户通报基于异常点探测和警报检索的可操作警报。在第一阶段,我们开发了一个高效的异常检测算法,称为Moving Metri探测器(MMD),以识别具有分布不可知性标准的计量标准之间的潜在警报。在第二个警报检索阶段,我们用反馈构建了额外的逻辑,以选择具有点向排序模型和商业规则的有效可操作警报。与其他趋势和季节性分解方法相比,我们的分解器更快、更好,可以探测出未监督的异常情况。我们的两阶段方法极大地提高了警报精确度,避免了eBay生产中的警报发出。