outlier 数据仓储与数据挖掘 教学 讲义.pptVIP

outlier 数据仓储与数据挖掘 教学 讲义.ppt

  1. 1、原创力文档(book118)网站文档一经付费(服务费),不意味着购买了该文档的版权,仅供个人/单位学习、研究之用,不得用于商业用途,未经授权,严禁复制、发行、汇编、翻译或者网络传播等,侵权必究。。
  2. 2、本站所有内容均由合作方或网友上传,本站不对文档的完整性、权威性及其观点立场正确性做任何保证或承诺!文档内容仅供研究参考,付费前请自行鉴别。如您付费,意味着您自己接受本站规则且自行承担风险,本站不退款、不进行额外附加服务;查看《如何避免下载的几个坑》。如果您已付费下载过本站文档,您可以点击 这里二次下载
  3. 3、如文档侵犯商业秘密、侵犯著作权、侵犯人身权等,请点击“版权申诉”(推荐),也可以打举报电话:400-050-0827(电话支持时间:9:00-18:30)。
  4. 4、该文档为VIP文档,如果想要下载,成为VIP会员后,下载免费。
  5. 5、成为VIP后,下载本文档将扣除1次下载权益。下载后,不支持退款、换文档。如有疑问请联系我们
  6. 6、成为VIP后,您将拥有八大权益,权益包括:VIP文档下载权益、阅读免打扰、文档格式转换、高级专利检索、专属身份标志、高级客服、多端互通、版权登记。
  7. 7、VIP文档为合作方或网友上传,每下载1次, 网站将根据用户上传文档的质量评分、类型等,对文档贡献者给予高额补贴、流量扶持。如果你也想贡献VIP文档。上传文档
查看更多
outlier 数据仓储与数据挖掘 教学 讲义.ppt

* Contents Outliers as Noises Distribution-based Outliers Depth-based Outliers Distance-based Outliers Density-based Outliers Deviation-Based Outlier Case Study Deviation-Based Outlier Detection Simulate a mechanism familiar to human being: after seeing a series of similar data, an element disturbing the series is considered an exception Sequential Exception Techniques OLAP Data Cube Techniques Sequential Exception Select subsets of data Ij (j=1,2,…,n) from the dataset I Compare the dissimilarity of I and (I-Ij) Find out the minimum subset Ij that reduce the disimuliarity the most Smoothing factor D is a dissimilarity function C is a cardinality function, for example, the number of elements in the dataset Example Ij I- Ij C(I- Ij) D(I- Ij) SF(Ij) {} {1,4,4,4} 4 1.69 0.00 {4} {1,4,4} 3 2.00 -0.93 {4,4} {1,4} 2 2.25 -1.12 {4,4,4} {1} 1 0.00 1.69 {1} {4,4,4} 3 0.00 5.07 {1,4} {4,4} 2 0.00 3.38 {1,4,4} {4} 1 0.00 1.69 Let the data set I be the set of integer values {1,4,4,4} Note, when Ij = {}, D(I) = D(I-Ij) = 1.69, SF(Ij)=0 When Ij={1}, SF(Ij) has the maximum value, so {1} is the outlier set OLAP Data Cube Technique Deviation detection process is overlapped with cube computation Precomputed measures indicating data exceptions are needed A cell value is considered an exception if it is significantly different from the expected value, based on a statistical model Use visual cues such as background color to reflect the degree of exception * Contents Outliers as Noises Distribution-based Outliers Depth-based Outliers Distance-based Outliers Density-based Outliers Deviation-Based Outlier Case Study * E-bay Fraud detection Virtual marketplaces: online auctions have been thriving as a business over the past decade. People from all over the world trade goods worth millions of dollars every day using these. EBay, the world’s largest auction site, reported a third quarter revenue of $1,449 billion, with over 212 million registered users . These figures represent a 31%

文档评论(0)

yuzongxu123 + 关注
实名认证
文档贡献者

该用户很懒,什么也没介绍

1亿VIP精品文档

相关文档