国外技术干货:Google Sibyl- A system for large scale supervised machine learning chandra

VIP免费
2024-12-10 1 0 630.88KB 28 页 5.9玖币
侵权投诉
Google Confidential and Proprietary
Sibyl: A system for large scale supervised
machine learning
Kevin Canini, Tushar Chandra, Eugene Ie, Jim McFadden, Ken Goldman, Mike Gunter,
Jeremiah Harmsen, Kristen LeFevre, Dmitry Lepikhin, Tomas Lloret Llinares, Indraneel
Mukherjee, Fernando Pereira, Josh Redstone, Tal Shaked, Yoram Singer
Google Confidential and Proprietary
Goal
Users respond differently to different information
in different contexts
Learn model of what information gets the best
user response in different contexts
... use model do decide what to present
Google Confidential and Proprietary
Uses of machine learning
Improve relevance
Improve site monetization
Reduce spam
Improve advertiser return on investment
... etc ...
Google Confidential and Proprietary
Problem scale
100M views per day (or more)
Businesses worth $100M (or more)
Google Confidential and Proprietary
Problem scope
There are many such problems at Google
Search, YouTube, Gmail, Android, G+, etc
Relevance, monetization, spam, etc
ML typically generates 10+% improvements
=> This is becoming an industry "best practice"
1% improvement is a big deal, e.g.:
Improves relevance for millions of users
Millions of dollars of revenue
=> accuracy is important
Google Confidential and Proprietary
Analysis tools
Machine learning architecture
Server
Impression log
Interaction log
... etc ...
User
Databases
Databases
Databases
"Joined" logs Machine learning
system
Machine learned model
摘要:

GoogleConfidentialandProprietarySibyl:AsystemforlargescalesupervisedmachinelearningKevinCanini,TusharChandra,EugeneIe,JimMcFadden,KenGoldman,MikeGunter,JeremiahHarmsen,KristenLeFevre,DmitryLepikhin,TomasLloretLlinares,IndraneelMukherjee,FernandoPereira,JoshRedstone,TalShaked,YoramSingerGoogleConfide...

展开>> 收起<<
国外技术干货:Google Sibyl- A system for large scale supervised machine learning chandra.pdf

共28页,预览6页

还剩页未读, 继续阅读

声明:本站为文档C2C交易模式,即用户上传的文档直接被用户下载,本站只是中间服务平台,本站所有文档下载所得的收益归上传人(含作者)所有。玖贝云文库仅提供信息存储空间,仅对用户上传内容的表现方式做保护处理,对上载内容本身不做任何修改或编辑。若文档所含内容侵犯了您的版权或隐私,请立即通知玖贝云文库,我们立即给予删除!
分类:计算机 价格:5.9玖币 属性:28 页 大小:630.88KB 格式:PDF 时间:2024-12-10

开通VIP享超值会员特权

  • 多端同步记录
  • 高速下载文档
  • 免费文档工具
  • 分享文档赚钱
  • 每日登录抽奖
  • 优质衍生服务
/ 28
客服
关注