基于数据挖掘的虚拟货币购买因素分析
摘要
网络作为二十世纪的新兴产物，越来越在人们的生活中发挥重要作用。虚拟货币作为二十一世纪网络经济发展的又一力作，适应了新时代的各种需要，满足了虚拟货币消费者购买的各种需求，发展前景无限广阔，拥有巨大的市场潜力。但是就目前情况来看，其发展阶段仍属于起步状态，并且由于其本身所特有的开放性和虚拟性，因而更加难以察觉和控制其伴生的风险。
本文第一章首先阐述了数据挖掘的相关理论，并对虚拟货币消费者购买行为分析进行分析，第二章阐述了数据挖掘理论，介绍了数据挖掘的特点和数据挖掘的一般过程以及数据挖掘的特点。第三章进行了虚拟货币消费者购买行为分析，包括客户关系的管理、CRM流程、虚拟货币消费者购买行为分析和虚拟货币消费者购买细分的方法，以及企业的虚拟货币消费者购买细分问题。第四章描述了虚拟货币消费者购买细分的案例，进行了数据预处理虚拟货币消费者购买聚类，以及细分客户消费行为分析。第五章进行了虚拟货币消费者购买的相关性分析，包括虚拟货币消费者购买购买的相关性虚拟货币消费者购买消费行为的分析，在第六章进行了总结与展望。 本文在虚拟货币消费者购买购买倾向上共进行了CART算法、CHAID算法和C5.0算法，这三种算法进行处理，最终的二道重要保持客户和年龄关系较大，重要挽留客户和消费频率关系较大，重要发展客户则和最近一次消费时间相关性高，一般价值客户和消费频率与消费金额有关，低价值客户则和性别有一定关系。针对此，在展开营销策划时，可以针对性进行营销。
关键词：虚拟货币 、RFM、客户细分、数据挖掘、CART算法、虚拟货币消费者购买行为
Network, as a new product of twentieth Century, is playing an increasingly important role in people's lives. As another effort of the development of the network economy in twenty-first Century, virtual currency adapted to the needs of the new era and met the various needs of the virtual currency consumers. The prospect of development is boundless and has great market potential. However, as far as the current situation is concerned, its development stage is still in its infancy, and because of its own unique openness and virtuality, it is more difficult to detect and control its associated risk.
The first chapter first expounds the theory of data mining, and analyzes the purchase behavior analysis of the virtual money consumer. The second chapter expounds the theory of data mining, introduces the characteristics of data mining, the general process of data mining and the characteristics of data mining. The third chapter analyzes the consumer buying behavior of virtual currency, including the management of customer relationship, the CRM process, the analysis of the purchase behavior of the virtual currency consumer and the method of the consumer purchase subdivision of the virtual currency, as well as the purchase and subdivision of the virtual currency consumer in the mobile communication enterprise. The fourth chapter describes the consumer purchase subdivision of virtual currency in mobile communication, and carries out the data preprocessing of virtual currency consumer purchase clustering, and the analysis of consumer consumer behavior. The fifth chapter carries out the correlation analysis of the consumer purchase of the virtual currency of mobile communication, including the analysis of the consumer buying behavior of the virtual currency consumer buying and buying, and the summary and prospect in the sixth chapter. In this paper, CART algorithm, CHAID algorithm and C5.0 algorithm have been carried out on the purchase and purchase tendency of mobile communication virtual money consumers. These three algorithms are handled. The final two ways are important to keep the relationship between customers and age larger. The important detainment customer and the consumption frequency are very important, the customer is to develop and the last time of consumption. High correlation and general value. Customers and consumption frequency are related to consumption amount. Low value customers are related to gender. For this purpose, marketing can be targeted for marketing.
Key words: virtual currency, RFM, customer segmentation, data mining, CART algorithm, virtual currency consumer purchase behavior
目录
摘要 1
ABSTRACT 2
1 绪论 7
1.1 研究背景 7
1.2 国内外研究现状 7
1.2.1 数据挖掘的研究现状 8
1.2.2 客户虚拟货币消费者购买行为研究现状 8
1.2.3基于数据挖掘的客户虚拟货币消费者购买行为研究现状 9
1.3 研究内容 9
1.4 本文组织结构 10
2 数据挖掘理论概述 11
2.1 数据挖掘特点 11
2.2 数据挖掘的一般过程 11
2.3数据挖掘常用方法 12
2.3.1 决策树方法 12
2.3.2统计分析方法 12
2.3.3粗糙集方法 12
2.3.4 贝叶斯网络 13
2.3.5 人工神经网络 13
2.3.6遗传算法 13
3 虚拟货币消费者购买行为分析 14
3.1客户关系管理 14
3.1.1 CRM目标 14
3.1.2 CRM的体系结构 15
3.1.3企业实施CRM的优势 15
3.2 CRM流程 16
3.3虚拟货币消费者购买行为分析 17
3.3.1虚拟货币消费者购买行为 17
3.3.2 虚拟货币消费者购买行为模式 18
3.3.3 虚拟货币消费者购买行为研究理论基础 19
3.4虚拟货币消费者购买细分方法 21
3.4.1 RFM分析 22
3.4.2 客户价值矩阵分析 25
3.5 企业的虚拟货币消费者购买细分问题 26
3.6 本章小结 27
4 虚拟货币消费者购买细分案例 28
4.1数据预处理 28
4.2虚拟货币消费者购买聚类 30
4.2.1 K-means聚类 32
4.2.2 Two-Step聚类 34
4.2.3 Kohonen聚类 36
4.2.4聚类结果比较 37
4.3细分客户消费行为分析 38
4.3.1重要保持客户 38
4.3.2重要发展客户 40
4.3.3重要挽留客户 41
4.3.4一般价值客户 42
4.3.5低价值客户 43
4.4 实证研究 44
4.4.1对某省电信运营商客户的细分 44
4.4.2 细分结果分析 45
4.4.3 研究结果的现实意义 46
5 虚拟货币消费者购买相关性 47
5.1虚拟货币消费者购买购买相关性 48
5.1.1CART算法原理 48
5.1.2CHAID算法原理 49
5.1.3 C5.0算法原理 49
5.2虚拟货币消费者购买消费行为分析 50
5.2.1重要保持客户CART消费分析 50
5.2.2重要挽留客户C5.0消费分析 52
5.2.3重要发展客户C5.0消费分析 55
5.2.4一般价值客户CHAID消费分析 57
5.2.5低价值客户CART消费分析 59
5.3实证研究的现实意义 60
6 总结与展望 62
6.1总结 62
6.2展望 62
致谢 65
参考文献 66
参考文献
[1]Srikant R. Mining Quantitative Association Rules in Large Relational Tables[J]. Acm Sigmod Record, 1996, 25:1--12.
[2]Liu G, Lu H, Yu J X, et al. AFOPT: An Efficient Implementation of Pattern Growth Approach[J]. Proceedings of the Icdm Workshop, 2003.
[3]Dong G, Li J. Efficient Mining of Emerging Patterns: Discovering Trends and Differences[J]. Proceedings of the Fifth Acm Sigkdd International Conference on Knowledge Discovery & Data Mining, 1999:43--52.
[4]杨辉, 王浣尘. 用于数据挖掘的粗集产生多重知识库的方法[J]. 上海交通大学学报, 1998, 32(12):111-114. DOI:10.1088/0256-307X/16/9/020.
[5]陈玉泉, 朱锡钧, 陆汝占. 文本数据的数据挖掘算法[J]. 上海交通大学学报, 2000, 34(7):936-938. DOI:10.3321/j.issn:1006-2467.2000.07.021.
[6]Fryer D S, Peters R D, Kim E J, et al. Dependence Of The Glass Transition Temperature Of Polymer Films On Interfacial Energy And Thickness[J]. Macromolecules, 2001, 34(16):5627-5634.
[7]Sengupta S, Bucklin L P. Organizing successful co-marketing alliances[J]. Journal of Marketing A Quarterly Publication of the American Marketing Association, 1993, 57:págs. 32-46.
[8]Johnson E J, Moe W W, Fader P S, et al. On the Depth and Dynamics of Online Search Behavior[J]. Social Science Electronic Publishing, 2004, 50(3):299-308.
[9]张玉峰, 晏创业. 基于Agent的个性化信息服务模型研究[J]. 情报学报, 2001, 20(5):555-559. DOI:10.3969/j.issn.1000-0135.2001.05.008.
[10]陈莉, 焦李成. Internet/Web数据挖掘研究现状及最新进展[J]. 西安电子科技大学学报：自然科学版, 2001, 28(1):114-119. DOI:10.3969/j.issn.1001-2400.2001.01.027.
[11]Kim J, Suh E, Hwang H. A model for evaluating the effectiveness of CRM using the balanced scorecard[J]. Journal of Interactive Marketing, 2003, 17(2):5--19.
[12]Chang H J, Hung L P, Ho C L. An anticipation model of potential customers’ purchasing behavior based on clustering analysis and association rules analysis[J]. Expert Systems with Applications, 2007, 32:753–764.
[13]向勇. 基于客户行为的汽车服务业库存管理研究[D]. 武汉理工大学, 2009. DOI:10.7666/d.y1474420.
[14]王振东. 聚类算法及其在客户行为分析中的应用研究[D]. 北京邮电大学, 2008.
[15]童建飞. 数据挖掘在电信客户行为分析中的应用研究[D]. 南昌大学, 2010.
[16]Berson A, Smith S J. Building Data Mining Applications for CRM[M]// Building Data Mining Applications for CRM. McGraw-Hill Companies, 1999.
[17]Data C. Data Mining: Concepts And Techniques[J]. San Francisco, 2010, 29(S1):1 - 18.
[18] Kimball, Ralph, and Margy Ross. The data warehouse toolkit: the complete guide to dimensional modelling. New York ua (2002). 125-150
[19] Nisbet, Robert, John Elder IV, and Gary Miner. Handbook of statistical analysis and data mining applications. Academic Press, 2009.
[20] Pawlak, Zdzisław. Rough set approach to knowledge-based decision support. European journal of operational research 1997, 99(1): 48-57.
[21] Friedman, Nir, Dan Geiger, and Moises Goldszmidt. Bayesian network classifiers. Machine learning 1997,29(2): 131-163.
[22] Mcculloch W S, Pitts W. A logical calculus of the ideas immanent in nervous activity[J]. Bulletin of Mathematical Biophysics, 1943, 5(4):99–115.
[23] Holland, John H. Adaptation in natural and artificial systems: an introductory analysis with applications to biology, control and artificial intelligence. MIT press, 1992.
[24] 中国客户关系管理网http://www.crmchina.com/web/research.asp?stype
[25] 汤兵勇.客户关系管理[M].北京:高等教育出版社.2003
[26] 陈玉保，刘宏，段红彬.营销理论的新发展:客户关系管理(CRM)理论[J].商业研究.2002.(14):77～79
[27] 梁小民.高级宏观经济学教程(上册)[M].北京:北京大学出版社，1993.111～111
[28] 符国群.虚拟货币消费者购买行为学(上)[M].北京:高等教育出版社，2001.23～23
[29] 陈静宇.基于一对一营销的客户行为模式研究[J],商业经济与管理,2003(3):19～23
[30]黄发良，钟智．用于分类的支持向量机．广西师范学院学报自然科学版．2004，9：75．78页．
[31]曲守宁，董彩云，徐德军，吴桐．关联规则算法研究及其在教学系统中的应用．计算机系统应用．2005，4：20．23页．
[32]韩永奇，张芸，姚玉霞．基于关联规则数据挖掘算法的应用．农业网络信息．2008，11：73．75页．
[33]何建忠，吕振俊．基于两个矩阵的关联规则挖掘优化算法．计算机工程．2008，1 7：56．61页．
[34]T，Swami Agrawal，Imielinski，A，Mining association rules between sets
of otems in large databases．proc．1 993 Acm Int．Conf．Management Of Data．Washington，DC．207·2 1 6P
[35] LAVIDGE R.J., and G．A. STEINER. A Model for Predictive Measurement ofAdvertising Effectiveness[J] .Journal of Marketing 25 (October 1961):59～62
[36] Dwyer F,Robert,Schurr Paul H,Oh Sejo.Developing Buyer-Seller Relations[J].Journal of Marketing,1987,51(4):11～28
[37] Suzanne Donner. What Can Customer Segmentation Accomplish?[J].BankerMagazine.1992,175(2):72～81
[38]段智敏，王如龙，孙美青．基于一卡通的数字化校园资源整合研究与实现．计算机工程与科学，2008，(1)：8．11
[39]罗可，蔡碧野数据挖掘及其发展研究．计算机工程与应用，2002，14(2)：182．184
[40]李峥嵘，柴彦威．大连城市居民周末休闲时间的利用特征．经济地理，1999
(5)：80-84
[41]周星．大学生日常休闲活动的动机与障碍．中国青年研究，2005，(8)：80—83
[42] Kadanoff.Marcia.Zoning and Cloning Your Best Customers[J].MC:MarketingComputers,1995, 15(8): 27～29
[43] Jim Sellers, Arthur Hughes. RFM Analysis:A New Approach to a Proven Technique[DB/OL]. http://www.relationshipmktg.com/FreeArticles/rmr017.pdf
