Mar 15–18, 2020

Introducing a new anomaly detection algorithm inspired by computer vision and RL

Tony Xing (Microsoft)
11:00am11:40am Tuesday, March 17, 2020
Location: 210 E

Who is this presentation for?

  • Data scientists, analysts, data engineers, and CTOs

Level

Intermediate

Description

Data-driven companies need to monitor various metrics (e.g., page views and revenue) of their applications and services in real time. Microsoft developed a time series anomaly detection service that helps customers monitor the time series continuously and alert for potential incidents on time.

Tony Xing outlines the pipeline and algorithm of Microsoft’s anomaly detection service, which is designed to be accurate, efficient, and general. The pipeline consists of three major modules, including data ingestion, experimentation platform, and online compute. To tackle the problem of time series anomaly detection, Microsoft developed a novel algorithm based on SR and CNN. This is the first attempt to borrow the SR model from the visual saliency detection domain to time series anomaly detection. Moreover, the company innovatively combined SR and CNN to improve the performance of the SR model. This achieves superior experimental results compared with state-of-the-art (SOTA) baselines on public datasets and Microsoft production data. Tony introduces the latest RL-based method to further advance the SOTA on top of work previously presented at KDD.

You’ll get a thorough walkthrough of challenges with SOTA methods such as the lack of labels, generalization, and efficiency; a system overview of how the combined novel algorithms and engineer system solves of those challenges such as data ingestion, online compute, and experimentation platform; Microsoft applications including AIOps serving Bing, Office, and Azure, Azure Cognitive Services, and a case study; methodology of SR and SR-CNN; the results superior to SOTA time series anomaly detection algorithms including the dataset, experiment method, KPIs (precision, recall, F1) compared to SOTA algorithms; and future work.

Prerequisite knowledge

  • A basic understanding of deep learning, statistical methods, and time series methods

What you'll learn

  • Discover a novel time series anomaly detection algorithm inspired by the computer vision deep learning domain, which is far superior to SOTA methods
  • Understand the application of the algorithm and system in cognitive services and AIOps in Microsoft
Photo of Tony Xing

Tony Xing

Microsoft

Tony Xing is a senior product manager on the AI, data, and infrastructure (AIDI) team within Microsoft’s AI and Research Organization. Previously, he was a senior product manager on the Skype data team within Microsoft’s Application and Service Group, where he worked on products for data ingestion, real-time data analytics, and the data quality platform.

Leave a Comment or Question

Help us make this conference the best it can be for you. Have questions you'd like this speaker to address? Suggestions for issues that deserve extra attention? Feedback that you'd like to share with the speaker and other attendees?

Join the conversation here (requires login)

Contact us

confreg@oreilly.com

For conference registration information and customer service

partners@oreilly.com

For more information on community discounts and trade opportunities with O’Reilly conferences

Become a sponsor

For information on exhibiting or sponsoring a conference

pr@oreilly.com

For media/analyst press inquires