myProgrames的博客

http://www.csdn.net/article/2015-01-30/2823783

http://blog.csdn.net/jbfsdzpp/article/details/47359739?ref=myread

如何通过自学，成为数据挖掘“高手”

百科中对今日头条技术特点的描述如下社交和用户行为分析：根据微博行为、阅读行为、地理位置、职业、年龄等挖掘出兴趣。通过社交行为分析，5秒钟计算出用户兴趣；通过用户行为分析，用户每次动作后，10秒内更新用户模型。自然语言处理和图像识别技术：对每条信息提取几十个到几百个高维特征，并进行降维、相似计算、聚类等计算去除重复信息；对信息进行机器分类、摘要抽取，LDA主题分析、信息质量识别、敏感词过

http://dataunion.org/13797.htmlhttp://www.wtoutiao.com/p/jd8dSc.htmlhttp://cio.it168.com/a2015/0806/1752/000001752658.shtmlhttp://www.csdn.net/article/2015-04-01/2824365

http://www.tuicool.com/articles/3iQNRbA

http://www.jasongj.com/tags/Kafka/

有几篇比较好的关于用户画像的文章，连接如下：http://dataunion.org/13797.htmlhttp://www.wtoutiao.com/p/jd8dSc.htmlhttp://cio.it168.com/a2015/0806/1752/000001752658.shtmlhttp://www.csdn.net/article/2015-04-01/

http://blog.csdn.net/desilting/article/details/45505121

http://www.cnblogs.com/ggjucheng/archive/2013/02/01/2888051.htmlhttp://blog.csdn.net/desilting/article/details/45505121

http://www.csdn.net/article/2015-04-24/2824545

http://tech.meituan.com/hive-sql-to-mapreduce.htmlhttp://blog.csdn.net/lifuxiangcaohui/article/details/40615843

http://www.csdn.net/article/2015-01-13/2823530http://www.cnblogs.com/xd502djj/p/3799432.htmlhttp://blog.csdn.net/fp196391196391/article/details/8302121http://www.aboutyun.com/thread-10557-1-

http://wenku.baidu.com/link?url=4WmWlm_O_jtvcOYfIrxxY03cCzMmGlqLP3Qn6iuusWHz34mkHr6l_xhpRAcXxXtUlq4-hMst51V97K9Z4cJ9tip7eS2Z42PSxJNXVpEsHjChttp://wenku.baidu.com/link?url=9HUNBbBkhMq002OGuGfutS03wOh

http://www.searchtb.com/2012/09/introduction-to-storm.html

http://www.uml.org.cn/sjjmwj/201409045.asp

http://wenku.baidu.com/link?url=6h6cjW2DwSJxV6Gxg9h3RwEzcW9T3_VzkdjNeIQYCYWruh3ewChi1UdSGZ00TLD5UrBKrmZRKHgWiz-XcSRusjTsjnWibe41Hpf_H1avgXa

http://www.07net01.com/linux/mahoutbeiyesisuanfakaifasilu_tuozhanpian_1_584428_1379145381.html

http://blog.fens.me/mahout-recommendation-api/

http://www.chinacloud.cn/upload/2014-02/14021808531904.pdf

http://www.cnblogs.com/zhangchaoyang/archive/2012/08/28/2660929.html

http://blog.csdn.net/zouxy09/article/category/1219263

http://www.cnblogs.com/liqizhou/archive/2012/05/28/2521255.html

http://blog.csdn.net/dc_726/article/details/18224365

http://www.07net01.com/linux/mahoutbeiyesisuanfakaifasilu_tuozhanpian_1_584428_1379145381.html

http://www.infoq.com/cn/articles/baifendian-recommendation-engine/

http://dataunion.org/11710.html?comefrom=http://blogread.cn/news/

http://tech.meituan.com/spark-tuning-pro.html