基于网购特征提取的顾客行为挖掘算法仿真  被引量:1

Simulation of Customer Behavior Mining Algorithm Based on Online Shopping Feature Extraction

在线阅读下载全文

作  者:李艳[1] 韩景灵[1] LI Yan;HAN Jing-ling(BusinessCollege of Shanxi University,Electronic C o m m e r c e,Taiyuan Shanxi 030031,Chnia)

机构地区:[1]山西大学商务学院,山西太原030031

出  处:《计算机仿真》2020年第5期150-153,234,共5页Computer Simulation

基  金:融合情境因素的电子商务推荐方法研究(Y2018016)。

摘  要:探究一种有效的顾客行为挖掘算法,可以提高挖掘加速比,减小误差率,保证行为挖掘的可靠性和实用性。为解决顾客行为挖掘处理存在误差较高,加速比较低等问题,提出基于网购特征提取的顾客行为挖掘算法。算法是依据交易属性从顾客行为条件属性的特征中提取能力,获取网购特征规则。利用正则化估计方法,极小化回归线估计值和方差特征参数估计值,并结合坐标算法和KKT条件,获取回归线和方差特征参数。利用网购准则挖掘出与回归线和方差特征参数对应的最佳挖掘结果,完成了顾客行为挖掘。仿真结果表明,所提算法可以有效提高挖掘加速比、减小误差率并能提高查全率和查准率。The effective customer behavior mining algorithm can improve the mining speedup ratio and reduce the error rate. In order to solve the problems of high error and low speedup ratio, this paper focuses on an algorithm to mine customer behavior based on online shopping feature extraction. Based on the ability that transaction attributes extracted the characteristics of customer behavior attributes, this algorithm obtained the rule of online shopping feature. Moreover, the regularization estimation method was used to minimize the estimation value of regression line and the estimation value of variance characteristic parameter. Meanwhile, the coordinate algorithm was combined with KKT condition to obtain the regression line and variance characteristic parameters. Finally, the best mining result corresponding to the regression line and variance characteristic parameters was mined by online shopping criteria. Thus, the customer behavior mining was completed. Simulation results prove that the proposed algorithm can effectively improve the mining speedup ratio, reduce the error rate and improve the recall rate and precision rate.

关 键 词:顾客行为 挖掘 挖掘加速 查全率 查准率 

分 类 号:TP311.13[自动化与计算机技术—计算机软件与理论]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象