摘要
研究数据预处理新技术,采用数据挖掘技术建立西部地区经济增长差异分析模型,在数据挖掘技术中采用决策树算法进行分析,克服现有算法的缺点,对现有算法进行改进优化,提高模型精度,得到省份分类情况及影响地区差距的主要相关要素.研究结果表明:相比于传统算法,数据挖掘技术更能找到数据间的内在规律,反映了数据挖掘寻找潜在数据规律的价值所在.
The new pretreatment technology research data,using data mining technology to analyze the model of the difference of economic growth in western region,the data mining technology in the decision tree algorithm analysis,to overcome the drawbacks of the existing algorithms,the improved optimization of the existing algorithm,improve the accuracy of the model,the main factors related provinces classification and influence the regional disparity.The results show that:compared with the traditional algorithm,the data mining technology can find the inherent law between the data and reflect the value of the data mining to find the potential data.
出处
《广西民族大学学报（自然科学版）》
CAS
2017年第4期64-68,共5页
Journal of Guangxi Minzu University ：Natural Science Edition
基金
广西教育厅科研项目(2017KY1261)
关键词
西部经济
差异性分析
数据挖掘
决策树
western economy
difference analysis
data mining
decision tree
