有序规则挖掘问题的研究

Research of mining ordering rules

许多关于数据挖掘和机器学习的研究都集中于分类的研究,然而现实世界涉及到的不仅仅是分类问题,比如对象的排序问题。将有序规则的挖掘问题加以形式化,挖掘有序规则即要找到各个属性产生的排序与对象整体排序之间的关系。提出了有序信息表的形式化概念,然后提出了通过将有序信息表转化为一个二值信息表,继而挖掘有序规则的方法。

Many real world problems deal with ordering objects instead of classifying objects, though most research in machine learning and data mining has been focused on the latter. The problem of mining ordering rules as finding association between orderings of attribute values and the overall ordering of objects is formulated. For mining ordering rules, the notion of information tables is proposed, then the approach to mining ordering rules is gaven by transforming the ordered information table into a binary information table.