摘要电子商务的迅速发展,促进了消费者的消费认识和企业经营理念的改变,客户逐渐从被动的接受者到主动的选购者。客户是企业发展的根本,现有客户的规模有限的,而潜在客户理论上是无限的,潜在客户的获得对企业扩大市场份额、提升自身竞争力有重要意义,因此潜在客户的挖掘越来越受到学者与企业的关注。B2C电子商务是针对商家(B)对一般消费者(C)的商务模式,以其进入门槛较低,受众范围更广等原因在近十年来获得巨大的发展。本文基于B2C电子商务平台自身特点及其客户特征,提出了基于WEB数据挖掘的潜在客户识别模型。首先,对数据挖掘基础进行了介绍。其次,介绍了B2C电子商务平台的自身定义,分析其客户特征,并针对这些特征提出基于web数据挖掘的潜在客户识别方法。该方法主要分为三大步骤:一是数据获取,本文主要研究的是web日志记录挖掘;二是数据预处理,包含数据清洗、数据转换、会话识别等方式;三是模式挖掘与解释,采用决策树、神经网络两种经典分类算法进行客户分类。最后,结合焦点科技 “新一站保险”的现实用户使用数据,进行实证分析。分析结果得出用户浏览页面数是影响用户购买的最重要因素,而浏览时间段与是否登录对分类结果影响最不显著。27018
关键词 潜在客户 web数据挖掘 分类分析 决策树 神经网络 毕业论文外文摘要
Title The Research on Potential Customer Recognition based on B2C Platform
Abstract
The rapid development of e-commerce, promotes the changes of consumption consciousness and the enterprise management. Customer is the foundation of enterprise development, and the scale of existing customer is limited but potential customers are theoretically unlimited. The acquirement of potential customers is of great significance to the expansion of enterprises. This study aims to use web data mining to identify potential customer. In this paper, introduces the basic theory of data mining from the beginning. Then, the definition of B2C platform and analysis of its customer’s characteristics are given. According to these characteristics, a potential customer recognition method based on Web data mining is proposed which contains three steps. First of all, getting data. Next is data preprocessing which includes data cleaning, data transformation, user identification and session identification. Third step uses decision tree and Neural Networks to uncover hidden knowledge, judging by this, mining potential customer. Finally, empirical analysis. Result shows that the number of customer’s browsing page is the most important factors affecting user’s purchase intention while browse time and whether login or not is not significant to the result of classification.
Keywords potential customer web data mining classification Decision tree Neural network
目 次
一 绪论 1
1.1 研究背景 1
1.2 研究意义 2
1.3 研究内容与思路 2
1.4 论文结构 3
二 数据挖掘理论基础 4
2.1 数据挖掘定义及过程 4
2.2 数据挖掘功能 5
2.3 数据挖掘中分类方法 6
三 B2C电子商务的客户分类 8
3.1 B2C平台概述 8
3.2 B2C电子商务客户分类——web数据挖掘 9