Finding Needle in a Million Metrics: Anomaly Detection in a Large-scale Computational Advertising Platform
This work addresses the challenge of anomaly detection for engineering teams in real-time bidding systems, but it appears incremental as it builds on existing monitoring approaches.
The paper tackles the problem of monitoring a large-scale computational advertising platform by developing a mechanism to recover representative metrics and detect behavioral changes, demonstrating its effectiveness through incident cases.
Online media offers opportunities to marketers to deliver brand messages to a large audience. Advertising technology platforms enables the advertisers to find the proper group of audiences and deliver ad impressions to them in real time. The recent growth of the real time bidding has posed a significant challenge on monitoring such a complicated system. With so many components we need a reliable system that detects the possible changes in the system and alerts the engineering team. In this paper we describe the mechanism that we invented for recovering the representative metrics and detecting the change in their behavior. We show that this mechanism is able to detect the possible problems in time by describing some incident cases.