基于C4.5算法的卷烟消费者购买行为的研究与分析  

Research and Analysis of Cigarette Consumers’ Purchase Behavior Based on C4.5 Algorithm

作　　者：蒋海浪 范剑波[1] JIANG Hailang;FAN Jianbo(School of Electronic and Information Engineering,Ningbo University of Technology,Ningbo,Zhejiang,315211,China)

机构地区：[1]宁波工程学院电子与信息工程学院

出　　处：《宁波工程学院学报》2019年第4期48-53,共6页Journal of Ningbo University of Technology

基　　金：浙江省大学生科技创新活动计划暨新苗人才计划项目(2018R428004)

摘　　要：决策树归纳算法已经成功地应用于许多应用领域的分类,通过分析决策树C4.5的算法,研究卷烟消费者的购买行为,利用问卷调查样本数据找出了卷烟消费者对卷烟的满意度。仿真实验结果表明,决策树测试结果符合率均在80%左右,具有较好的稳定性。满意度决策树规则符合卷烟行业的实际情况,对卷烟行业的生产和销售有一定的指导意义。Decision tree induction algorithm has been successfully applied in many application areas.By analyzing the algorithm of decision tree C4.5, the paper studies the purchase behavior of cigarette consumers as well as the satisfaction of cigarette consumers to cigarettes by using the sample data of questionnaire survey. The simulation results show that the coincidence rate of decision tree test results is about 80%, and it has good stability. The satisfaction decision tree rules are in line with the actual situation of the cigarette industry and have certain guiding significance for the production and sales of the cigarette industry.

关 键 词：C4.5算法 卷烟消费者 满意度 MATLAB 

分 类 号：TP39[自动化与计算机技术—计算机应用技术]