王瑞鑫, 刘万春. 商业数据挖掘中的核心算法[J]. 北京工业大学学报, 2004, 30(4): 510-514.
    引用本文: 王瑞鑫, 刘万春. 商业数据挖掘中的核心算法[J]. 北京工业大学学报, 2004, 30(4): 510-514.
    WANG Rui-xin, LIU Wan-chun. The Core Algorithm in Business Data Mining[J]. Journal of Beijing University of Technology, 2004, 30(4): 510-514.
    Citation: WANG Rui-xin, LIU Wan-chun. The Core Algorithm in Business Data Mining[J]. Journal of Beijing University of Technology, 2004, 30(4): 510-514.

    商业数据挖掘中的核心算法

    The Core Algorithm in Business Data Mining

    • 摘要: 为了使企业的管理层能够根据市场需求进行数据挖掘,并基于挖掘出来的规则做出决策,在数据仓库、粗糙集方法等理论的基础上提出了一种核心算法,应用于商业数据挖掘.核心算法从信息表开始,通过属性泛化、求核心属性、属性归约,最终得到由正确率表示的规则.在求核心属性的部分对粗糙集理论中求核心集的方法进行了改进,并给出了相应的证明.核心算法利用SQL语言的功能强大、容易开发、运行稳定等特点,通过SQL语言编程来实现.核心算法具有针对性强、可操作性强等优点.

       

      Abstract: In order to help the management group of a company to mine data according to different business requirements and make decisions based on the rules that come from data mined, the authors present a core algorithm, which is based on the theory of data warehouse, rough set method, etc., and then used to mine the business data. Core algorithm starts from the information table which generates from the business requirements, and then conducts the generalization of attribute, calculates the core attribute, processes attribute reducing. At last, the rules that are described by accuracy are made. It makes improvement to the 'core set' of rough set theory in the part of calculating the core attribute, and also proves its validity. Core algorithm is implemented by SQL language programming since SQL language has such advantages, as powerful function, easy to be developed, running stable. The core algorithm focuses on business goals and can be manipulated easily.

       

    /

    返回文章
    返回