大数据时代算法前沿.pdf

超大规模用户数据挖掘和推荐算法 最新进展 (从KDD-CUP 2012谈起) ( KDD-CUP 2012 ) (( KKDDDD--CCUUPP )) Gordon Sun 孙国政（ ） Chief Scientist， Tencent Inc. 2012.9.8 目录 目录 互联网时代：大数据时代 • Every day, we create 2.5 quintillion bytes of data. IBM （ ） • Data will grow 50X in the next 10 years. IDC （ ） • By the end of 2012 90+% of Fortune 500 having ‘big data’ initiatives. （Deloitte） 大数据：是烦恼还是商机？ • IT and business managers have more concerns than enthusiasm about Big Data implementation. – Systems collecting, storing, managing and analyzing information are expensive. • If US healthcare were to use big data creatively and effectively to drive efficiency and quality, the sector could create more than $300 billion in value every year. （McKinsey） 大数据的挑战 • But making more data available is just one-half of the big data equation. The other half is how we make sense of that data. For data to become information (and ultimately knowledge), it must be interpreted…. • And, used for us people! • � User-centric domain-comprehensive intelligent service. 目录 KDD- CUP 2012 （sponsored by Tencent） 超大规模用户数据处理和推荐算法的国际比赛 • Track 1: Predict which users (or information sources) one user might follow in Tencent Weibo. • Track 2: Predict the click-through rate of ads given the search query and user information. / Track 1: B