论文:Exceptional Model Mining-duivesteijn2015,
Supervised Descriptive Pattern Mining-Book
特殊模型挖掘(EMM):(Exceptional Model Mining)
总结:异常模型
前提:基于分类结果
属性分为描述性属性、目标属性,目标属性用于判别该子组是否异常。
方法:在不同的子组及补集和全集上分别计算目标属性之间的关系
判别:基于目标属性建立模型,用于评估目标属性之间的关系,若子组上目标属性的关系模型与补集、全集的目标属性的关系模型不同,则该子组是异常的。可建立多种模型,并基于模型得到该子组兴趣度(quality-measure)。
Having generated candidate subgroups to evaluate, for each subgroup under consideration we induce a model on the targets, learning the model from only the data belonging to the subgroup. Then, this model is evaluated with the designed quality measure, to determine which subgroups are the most interesting ones.The typical quality measure in EMM indicates how exceptional the model fitted on the targets in the subgroup is, compared to either the model fitted on the targets in its complement, or the model fitted on the targets in the whole dataset。
可选的模型:相关性-相关性系数;关联-;线性回归-判断斜率;分类模型-;贝叶斯模型;一般线性回归-。
最后
以上就是开朗画板最近收集整理的关于特殊模型挖掘(EMM)的全部内容,更多相关特殊模型挖掘(EMM)内容请搜索靠谱客的其他文章。
发表评论 取消回复