Intelligent Anomaly Detection in Heterogeneous Internet Services

Thursday, December 8, 2016 - 4:45pm5:30pm

Dong Wang, Baidu Inc.

Abstract: 

When talking about anomaly detection in Internet services, most of us usually imagine a scenario in which lots of curves monitor the various metrics and some fixed thresholds tell something wrong. However such simple ways are far from effective nowadays. In the talk I am going to address many machine learning based intelligent approaches to do anomaly detection in lots of heterogeneous Internet services. All of the services mentioned here are from one of the top IT companies in the world, Baidu, whose business includes search engine, location based service (LBS), finance and payment, etc. The total users they cover are more than one billion. The approaches mentioned in this talk are already actively used in Baidu’s real products.

Dong Wang, Baidu Inc.

Dong Wang is a principal architect at Baidu, the largest search engine in China, and has led Baidu’s SRE team to work on some challenging projects, such as automatic anomaly detection and issue fixing in large scale Internet sites. He is also interested in user experience improvement in the mobile Internet services. Prior to Baidu, he worked at Bell Labs and Google for more than 15 years in total.

LISA16 Open Access Sponsored by Bloomberg

Open Access Media

USENIX is committed to Open Access to the research presented at our events. Papers and proceedings are freely available to everyone once the event begins. Any video, audio, and/or slides that are posted after the event are also free and open to everyone. Support USENIX and our commitment to Open Access.

BibTeX
@conference {201537,
author = {Dong Wang},
title = {Intelligent Anomaly Detection in Heterogeneous Internet Services},
year = {2016},
address = {Boston, MA},
publisher = {{USENIX} Association},
month = dec,
}

Presentation Video

Presentation Audio