摘要
当前,贫困生认定体系薄弱、不规范,如何认定贫困生已经成为国内高校及社会关注的热点问题。为完善贫困生认定体系,将数据挖掘技术引入到贫困生认定工作中,提出基于加权约束的决策树认定方法。该方法首先确定源数据——高校多个部门管理系统中的数据。其次,对数据进行分析处理确定贫困生认定指标属性,并对属性进行量化处理。最后,基于加权约束的决策树方法建立贫困生认定决策树。实践证明,该方法提高了贫困生认定效率,保证了贫困生认定工作的公平、公正性,并为决策提供了重要依据。
At present,the impoverished students identification system is inadequate and not standardised,it has become the focus of atten-tion in universities and the society of China that how to identify the impoverished students.In order to perfect the impoverished students identi-fication system,in this paper we introduce data mining to the work of impoverished students identification,and propose a weighted constraints-based decision tree identification method.The method first determines the source data,which refers to the data in management systems of dif-ferent departments in universities.Secondly,it analyses and processes the data to determine the indexes attributes of impoverished students identification,and makes the quantification process on these attributes.Finally,it builds the decision tree of impoverished students identifica-tion based on the decision tree method of weighted constraints.Practice proves that this method improves the efficiency of impoverished students identification,ensures the fairness and justice of the impoverished students identification work,and provides an important basis for the decision making in regard to impoverished students.
出处
《计算机应用与软件》
CSCD
北大核心
2014年第12期136-139,共4页
Computer Applications and Software
基金
河北省自然科学基金项目(F2012209019)
河北联合大学科学研究基金项目(z201246)
关键词
贫困生认定
数据挖掘
认定标准
数据预处理
公正性
Impoverished students identification
Data mining
Identification criteria
Data preprocessing
Fairness
