1
Raghu RamakrishnanResearch Fellow
Chief Scientist, Audience and Cloud Computing
Yahoo!
Purple Clouds: Data-Management@Yahoo!
2
Research Projects(in Audience Science and Y! Research)
• Content optimization (AS, Y!R)• Cloud Computing (Y!R)
– Hadoop, Pig, Sherpa
• Information extraction (Y!R)
• Mail spam (AS, Y!R))• Search & Advertising (Y!R)
Today’s talks
Lots more going on!
3
Yahoo! Home Page Featured Box
• It has four tabs: Featured, Entertainment, Sports, and Video
Online Models for Content Optimization (NIPS 2008) D. Agarwal, B. Chen, P. Elango, N. Motgi, S. Park, R. Ramakrishnan, S. Roy, J. Zachariah
4
Novel Aspects
• Classical: Arms assumed fixed over time– We gain and lose arms over time
• Some theoretical work by Whittle in 80’s; operations research
• Classical: Serving rule updated after each pull– We compute optimal design in batch mode
• Classical: Generally. CTR assumed stationary– We have highly dynamic, non-stationary CTRs
5
Comparing buckets
6
Audience—Research Collaboration
Yahoo! Research
• Deepak Agarwal• Bee-Chung Chen• Wei Chu• Pradheep Elango• Raghu Ramakrishnan • Seung-Taek Park
Audience Engineering
• Todd Beaupre• Kenneth Fox• Nitin Motgi• Scott Roy• Joe Zachariah
7
babycenter
epicurious
Search Results of the Future
yelp.com
answers.com
webmd
Gawker
New York Times
8
DBLife
Integrated information about a (focused) real-world community
Collaboratively built and maintained by the community
CIMple software package
9
10
Opening Up Yahoo! SearchPhase 1 Phase 2
Giving site owners and developers control over the appearance of Yahoo!
Search results.
BOSS takes Yahoo!’s open strategy to the next level by providing Yahoo!
Search infrastructure and technology to developers and companies to help them
build their own search experiences.
11