用户名: 密码: 验证码:
银行数据挖掘的运用及效用研究
详细信息    本馆镜像全文|  推荐本文 |  |   获取CNKI官网全文
摘要
当今信息化社会,网络经济与虚拟经济日新月异,促进金融行业的经营管理模式产生重大变革,金融市场由供给模式向需求模式转变。在市场竞争越来越充分的大趋势下,数据的商业与经济价值受到广泛关注,已演变为银行一项特殊的专用性资产,在传统资产价值理论基础上,具有其特殊性与相关性。银行数据挖掘的运用及效用研究将金融学、信息技术、管理科学有机结合,认为数据作为银行重要资源禀赋之一,是生产运营过程的产物,技术与管理发展水平的标志,经济人偏好的体现,制度约束的基础。
     现代银行依托于可量化分析的数据与数据模型,通过更加精细化管理创造价值,提高银行核心竞争力。本文以数据为主线,详细阐述数据在银行前台客户服务、中台风险管控和后台运营支持等各项活动中的作用,同时深入分析客户交易行为和经营管理活动中所产生数据的效用。从数据效用理论、数据治理、客户关系管理、全面风险管理、金融创新几个角度将数据作为银行重要资产所创造的价值展开研究,从而引申出数据有效性对银行各项业务的影响,及数据效用对银行价值创造的重要性。
     银行数据效用体现在两个方面,一是未经加工处理的原始数据量巨大,但是所蕴含的价值较小,运用技术手段和管理手段对数据进行整合、分类、清洗等加工处理后,数据就实现价值增值,对数据的进一步深入挖掘分析更是脑力劳动与人类智慧的体现,具有经济学意义上的效用;二是有效的数据在银行内部各个业务领域应用广泛,将数据效用应用到银行的各项价值增值活动后,可以显著提高银行综合管理水平与金融创新能力,最终实现银行价值的增值,为银行在未来金融市场竞争中提升核心竞争能力奠定坚实基础。
     本文的第一章综述银行数据挖掘、运用及效用研究的主要文献。从数据挖掘与应用理论、数据效用、信息理论、知识理论四个方面对国内外相关文献进行解读,并指出现有数据挖掘运用与效用理论研究方面的不足之处。
     第二章围绕银行数据效用和数据治理的有效性研究展开。在全面阐述数据内涵与外延的基础上,第二节结合银行业务发展特点论述数据效用的实现途径,通过对原始数据收集、清洗、加工、处理及整合后,实现数据的模型化,然后运用数据挖掘的分类、聚类等方法,对数据进行深入分析,提炼出有价值的信息,这些信息得以有效利用后,转化为指导银行管理经营决策的专用性知识型资产。最后知识型资产又以数据的形式保存下来,通过数据的流转发挥更大的价值。第四节研究数据治理的现状及发展趋势为数据效用的提升提供制度保障,主要强调数据治理作为公司治理的重要组成部分,其数据治理组织结构建设、数据标准化、数据质量管控,数据架构规划以及数据安全管理对提高银行经营管理水平的重要意义。并基于信息经济学理论,创新性地设计有效防止数据产生者违规道德风险发生的数据质量管控模型,避免数据生成过程中的道德风险给银行带来福利损失。
     第三章研究的主要内容是银行客户管理过程中数据的价值增值。银行的经营战略已经从以产品为中心向以客户为中心转变,优化客户关系管理工具与方法,挖掘数据的价值可以提升客户服务水平,为客户创造价值的同时实现银行自身的价值创造。第一节分析银行运用先进信息技术,建设客户信息管理系统的重要意义。文章详细论述数据在客户细分、客户行为分析、客户利润贡献度分析与精准营销中的价值增值。
     第四章数据在银行风险管理中的效用研究突出由于风险管理在银行的重要性、复杂性与技术依赖性,需要管理实践中将定性管理与定量分析有机结合,科学利用风险管理技术与信息技术对银行海量数据进行深度挖掘分析,既是监管制度的强制性要求,又是银行自身提高风险识别与计量效率,节约风险管理工作整体投入成本的必然选择。数据在银行信用风险、市场风险、操作风险管理中的有效运用,使风险管理创造的价值最大化。
     第五章将金融发展理论与金融创新理论结合,论述金融创新与客户关系管理、风险管理的关系,探索银行产品、服务和流程创新中的数据效用。揭示打造流程银行,金融产品创新与服务创新与提升数据效用的相关性,阐述建设企业级知识库,加强数据服务对于金融创新的重要意义。
     论文的主要创新点为:一是将数据作为银行的专有重要战略资源,分析其在银行利润增长、客户关系管理、风险管理、金融创新及构成竞争优势的价值贡献;二是运用信息经济学静态博弈模型,委托-代理理论设计银行内部数据治理机制与质量管控模型;三是以数据为主线将金融理论同信息技术理论有机融合,进行银行内部应用及金融创新过程中数据效用增值的研究。
In today’s information society, rapidly changed Internet economy and virtualeconomy urge the financial industry to make revolutions on their management patterns.The financial market is shifting from the supply model to the demand model. With thetrend that the market competition becomes more fiercely, the business and economicalvalue of data have attracted widely attentions and become a special and professional assetin banks. It bases on the traditional asset value theories and has its special and relativecharacteristics. The study of data mining application and utility in bank combinesfinance theories, information technologies, and management science organically. Itconsiders the data as one of important resource endowments of banks, as the output ofthe operation processes, as the indicator of technology and management capability, as thereflection of the economic man preference, and as the foundation of the institutionalconstraints.
     Modern banks rely on the data quantity analysis and data models to create values bymore meticulous management so that they can improve their core competitiveness. Thisarticle focuses on data; describes its functions at a great length on kinds of activities suchas front-end customer services, middle-end risk controls, and back-end operationalsupports; and analyzes the data utility generated during customer transaction activitiesand operational managerial activities in great depth. This article studies the value ofdata as one of important bank asset from many aspects including data value theory, datagovernance, customer relationship management, comprehensive risk management andfinancial innovations; and then extend the study to the impact of data validation on bankbusiness and the importance of data on the value creation in banks.
     The data utility of banks reflects in two ways. One comes from the processing ofdata. The unhandled raw data is huge in quantity but little in value. After applyingtechnical and managerial methods to integrate, classify and cleanse, data realized valuesadded. The deeper mining and analysis on data is the gathering of mental efforts andhuman intelligence. It has utility in economy and real use value in practice. The othercomes from the application of data, especially the wide applications of the validated datathroughout lines of business in banks. By applying data utility into kinds of banks’value-added activities, the comprehensive management capability and financialinnovation can be improved dramatically. Finally, the bank’s value and assets can be increased in order to form a steady foundation to improve the core competitiveness infuture financial market competition.
     The chapter one of this article gives an overview of the main documents in the fieldof bank data mining application and utility study. It studies and analyzes those relativedomestic and international documents which cover value theory, data application anddata mining theory, information theory and knowledge theory; it also point out theweakness point in the current data mining application and utility theory.
     The chapter two expands the discussion around utility of banks’ data and theeffectiveness of data governance. After expounding the intension and extension of datadefinition, combining the characteristics of bank business, the section two specifiesapproach methods of data utility. The raw data has to be collected, cleansed,manipulated, processed and integrated to achieve modularized data. Then we can usethe cluster analysis and the classification analysis of the data mining to study data, refineand summarize the useful information. With effective utilizations, this information willbecome the professional knowledge assets which can guide the management to makebusiness decisions. Finally, this kind of knowledge assets will be kept in a data form,which will play a more important role via data movement and circulation. The sectionfour studies the data governance’s current situation and development trends to provideregulation guarantees for the improvement of data utility. As the data governance is oneof important components of company governance, this section emphasizes theimportance of organizational structure development of data governance, datastandardization, data quality control, data architecture plan and data safety managementon the improvement of the bank operation and management. This chapter alsoinnovatively designs the data quality controlling model to prevent ethics risks generatedby illegal operations from the data producers effectively, then to avoid wealth loss duringthis process.
     The main content of the chapter three is the data utility increase during the bankcustomer management process. Banks’ operational strategies have shifted fromproduct-oriented to customer-oriented. They try to optimize tools and methods ofcustomer relationship management, to improve customer services by mining data value,to create values for both customers and bank their own. The section one analyzes theimportance of utilizing advanced information technologies and building customerinformation management systems for banks. The article elaborates the customer classification, customer behavior analysis, customer profitability analysis and the datavalue increase in the precision marketing.
     The chapter four, the study on the utility of data in the risk management of bank,states that due to the importance, the complexity and the technology-dependence of therisk management in banks, we need to combine the qualitative management andquantitative analysis together in the management practice, and to use risk managementtechnology and information technology to mine and analysis on massive data of banks indepth. It is both the mandatory requirements of the regulatory system and the inevitablechoice for banks to improve their risk identification and measurement efficiency and tosave the overall cost of risk management. Effectively using data in management ofcredit risk, market risk and operational risk can maximize the value created by the riskmanagement.
     The chapter five combines the financial development theory and the financialinnovation theory, discusses the relationship between financial innovation and customerrelationship management, risk management, and explore the value of banking products,services and process innovation in the data. It reveals the correlation between thebuilding of the process banking, the financial product innovation, the service innovationand the improvement of the data utility. It explains the importance of buildingenterprise-class knowledge base and strengthening data services on the financialinnovation.
     The main innovations of this article are as follows: first, it treats data as animportant strategic resource of banks and analyzes its contribution to the growth of bankprofits, the customer relationship management, the risk management, the financialinnovation and all these competitive advantage; second, it uses the informationeconomical static game model and principal-agent theory to design the bank's internaldata governance mechanisms and data quality control model; third, it merges thefinancial theory with the information technology based on data and studies the data utilityincrease in banks’ internal applications and in the financial innovations.
引文
①高鸿业西方经济学(第三版)中国人民大学出版社PP70-112②平狄克鲁宾费尔德微观经济学(第四版)中国人民大学出版社PP145
    ①中国银行业协会普华永道著,中国银行家调查报告2010,中国金融出版社,2010,pp88。
    ①菲利普·科特勒市场营销管理(亚洲版)中国人民大学出版社1996pp35-58
    ①克里斯.安德森长尾理论2.0中信出版社2009pp35-48
    ②李庆莉挖掘数据价值推动业务发展中国金融电脑2010(7) pp12
    ①杨永恒客户关系管理:价值导向及使能技术东北财经大学出版社2002PP137-146
    ①约翰·梅纳德凯·恩斯就业、利息和货币通论1936PP325-343
    [1] Adam Rombel. CRM Shifts to Data Mining to Keep Customers[J]. GlobalFinance,2001,15(11):97-98.
    [2] Alex Berson,Stephen Smith,Kurt Thearling. Building Data Mining Applications for CRM[M].America:McGraw-Hill Companies,Inc.,2000.
    [3] Anitesh Barua, Deepa Mani, Rajiv Mukherjee. Impacts of Effective Data on OperationalEfficiency. Working Paper.University of Texas at Austin, Indian School of Business,2010.
    [4] Anitesh Barua, Deepa Mani, Rajiv Mukherjee, Impacts of Effective Data on BusinessInnovation and Growth. Working Paper.. University of Texas at Austin, Indian School ofBusiness,2010.
    [5] Anitesh Barua, Deepa Mani, Rajiv Mukherjee, Measuring the Business Impacts of EffectiveData. Working Paper. University of Texas at Austin, Indian School of Business,2010.
    [6] Brett W.Gow. Effective Data Governance in Banking-Failure is Not an Option. WorkingPaper.IBM Global Business Services,2006.
    [7] ChenLei-da,Sakaguchi,Toru.N.frolick.Data mining methods applications tools[J].InformationSystems Management,2000,17(1):65-70.
    [8] Darryll Hendricks.Evaluation of Value-at-Risk Models Using Historical Data[J]. FRBNYEconomic Policy Review,1996,(4):39-69.
    [9] Douglas W.Diamond. Financial Intermediation and Delegated Montoring[J]. Market forInformation and the Origin of Financial Intermediation Review of Economic Studies,1984,(1):393-414.
    [10] Erik Brynjolfsson, Lorin M.Hitt, Heekyung Hellen Kim. Barua, How Does Data-DrivenDecisionmaking Affect Firm Performance?. Working Paper. MIT and NBER,2011.
    [11] Franklin Allen. The Market for Information and the Origin of FinancialIntermediation[J].Journal of financial Intermediation,1990,(1):3-30.
    [12] G. Davis, M. Olsont. Management information Systems: Coneptual Foundations, Structure andDevelopment[M]. New York: McGraw-Hill,1985.
    [13] George A. Akerlof.The Market For “Lemmons”:Quality Uncertainty And The MarketMechanism [J].The Quarterly Journal of Economics,1970,84(3):488-500.
    [14] George J. Benston, Clifford W.Smith. A Transactions Cost Approach To the Theory of FinancialIntermediation[J].The Journal of Finance,1976,(31):215-231.
    [15] H.E.Leland, D.H.Pyle. Informational Asymmetries, Financial Structure and FinancialIntermediation[J]. Journal of Finance,1977,32(2):371-387.
    [16] JIH W K. Effects of knowledge management on electronic commerce:an exploratory study intaiwan[J].Journal of Global Information Management,2005,13(4):1-24.
    [17] Joseph E.Stiglitz, Andrew Weiss. Credit Rationing in Markets with Imperfect Information[J].The American Econmic Review,1981,71(3):393-410.
    [18] K. A. Taipale. Data Mining And Domestic Security: Connecting The Dots To Make Sense OfData [J]. The Columbia Science and Technology Law Review,2003,(5):21-33.
    [19] Loveman, G. Diamonds in the Data Mine[J]. Harvard Business Review,2003,81(5):109-13.
    [20] McAfee. A."The Impact of Enterprise Information Technology Adoption on OperationalPerformance: An Empirical Investigation."[J].Production and Operations Management,2002,11(1):33-53.
    [21] Malhotra,Rashmi,Malhotra,D.K., Differentiating between good credits and bad credits usingneuro-fuzzy systems[J]. European Joumal of Operational Research,2002,(136):190-211.
    [22] Odom M.D.,Sharda R. A neural network for bankruptcy prediction [J]. International JointConference on Neural Networks,1990(2):163-168.
    [23] Paolo Giudici, Robert Castelo. Association models for web mining[J].Data Mining andKnowledge Discovery,2001,(5):183-196.
    [24] Patrick de Fontnouvelle, Virginia DeJesus-Rueff,John Jordan, Eric Rosengren. Using Loss Datato Quantify Operational Risk. Working Paper.Federal Reserve Bank of Boston,2003.
    [25] Rakesh Niraj,Mahendra Gupta, Chakravarthi Narasimhan. Customer Profitability in SupplyChain[J]. Journal of Marketing,2001,l(65):1-16.
    [26] R. Groth. Data Mining: Building competitive advantage[M]. Prentice-Hall Ptr,1999.
    [27] Richard Kittler,Weidong Wang.The emerging role for data mining[J].Solid State Technology,1999,42(11):45-50.
    [28] Ralph Kimball,Margy Ross,Warren Thomthwaite,Joy Mundy,Bob Becher. The DataWarehouse Lifecycle Toolkit(Second Edition)[M]. Wiley Publish,Inc,2009.
    [29] Ronald H. Coase. The Nature of the Firm[J]. Economica,1937,4:386-405.
    [30] Robert C. Merton. A Functional Perspective of Financial Intermediation[J].FinancialManagement,1995,24(2):23-41.
    [31] Saunders, Anthony. Financial Institutions Management: A Modern Perspective[M].Boston:Richard D.Irwin Inc,2000.
    [32] Shields Michael D. Research in management accounting by north americans in1990S[J].Journal of Management Accounting Research,1990,9:3-6.
    [33] Tsunesaburo Makiguchi. Philosophty of Value [M]. Tokyo:Seikyo Press,1964.
    [34] X. Freixas and J. Rochet. Microeconomics of Banking[M]. America:MIT Press,1997.
    [35]艾林.基于数据挖掘技术的金融机构操作风险研究[D].重庆:重庆大学(硕士学位论文),2006:
    [36]奥利弗·E.威廉姆森,西德尼·G.温特.企业的性质[M].北京:商务印书馆,2009.
    [37]奥利弗·威廉姆森,斯科特·马斯滕.交易成本经济学[M].李自杰,蔡铭等译.北京:人民出版社,2008.
    [38]伯纳德·利奥托德马克·哈蒙德.商务智能[M].北京:电子工业出版社,2005.
    [39]陈和智.现代商业银行核心竞争力研究[D].成都:西南财经大学(博士学位论文),2008:
    [40]陈劲,王焕祥.演化经济学[M].北京:清华大学出版社,2008.
    [41]陈忠阳.信用风险量化管理模型发展探析[J].国际金融研究2000,(10):14-19.
    [42]戴相龙,吴念鲁.商业银行经营管理[M].北京:中国金融出版社,1998:18-22.
    [43]邓正来著.哈耶克读本[M].北京大学出版社,2010.
    [44]冯琼,叶涛.论数据挖掘技术在客户价值管理中的应用[J].中国商界,2009,(6):204-205.
    [45]弗雷德里克·S.米什金.货币金融学[M].北京:清华大学出版社,2009.
    [46]高军,王睿.论利用数据挖掘技术提高商业银行市场风险管理水平[J].现代管理科学,2007,(8):58-59.
    [47]高印朝.商业银行价值管理研究[M].上海:上海财经大学出版社,2009.
    [48]郭友.我国股份制商业银行战略转型研究:基于竞争力视角[D].成都:西南财经大学(博士学位论文),2007:
    [49]郭熙铜.基于数据流视角的商业流程整合研究[D].合肥:中国科学技术大学(博士学位论文),2010:
    [50]韩明.基于流程理论的商业银行价值管理研究[M].北京:中国金融出版社,2010.
    [51]何荣勤. CRM原理、设计、实践(第2版)[M].北京:电子工业出版社,2006.
    [52]何绍华,康斌.信息价值和信息服务价值评价研究[J].图书情报工作,2005,(5):72-75.
    [53]黄宪,程翔,郑忠良.信息披露管制的若干新趋势[N].光明日报,2007,4(9):8
    [54]黄宪,马理,代军勋.资本充足率监管下银行信贷风险偏好与选择分析[J].金融研究,2005,(7):95-103.
    [55]黄宪,赵征.开放条件下中国银行业的控制力与国家金融安全[M].中国金融出版社,2009.
    [56] IBM中国商业价值研究院.洞察中国[M].北京:东方出版社,2008:63.
    [57]金建国,于立勇.新巴塞尔协议下的操作风险与我国银行业的应对策略[J].商业研究,2005,(21):162-164.
    [58]克里斯·安德森.长尾理论2.0[M].北京:中信出版社,2009.
    [59]李菁华.电子金融服务顾客关系质量评价模式的实证研究[M].上海:上海财经大学出版社,2009.
    [60]李金迎,詹原瑞.金融行业的数据挖掘技术研究[J].现代科学管理,2009,(8):14-16.
    [61]李洪梅.行为金融学中效用函数的发展应用研究[J].商业时代,2011,(28):61-62.
    [62]李庆莉.挖掘数据价值推动业务发展[J].中国金融电脑2010,(7):11-12.
    [63]刘君,宗承刚.信息资产创造价值的功能[J].财务与会计,2011,(3):29-30.
    [64]刘朝华.基于客户价值的客户分类模型研究[D].武汉:华中科技大学(博士学位论文),2008:
    [65]刘燕,吴凡.银行与第三方支付平台企业的微妙关系-合作与竞争[J].商业文化,2007,(5):32-33.
    [66]马超群,兰秋军,陈为民.金融数据挖掘[M].北京:科学出版社,2007:130-159.
    [67]马克卢普.美国的知识生产与分配[M].孙耀君译.北京:中国人民大学出版社,2007.
    [68]迈克尔.波特.竞争优势[M].陈小悦译.北京:华夏出版社,2004.
    [69]潘敏.商业银行公司治理:一个基于银行业特征的理论分析[J].金融研究2006,(3):37-47.
    [70]饶育蕾,盛虎.行为金融学[M].北京:机械工业出版社,2010.
    [71] Rober Hillard.信息驱动的商务[M].李姝芳,郭俊平,祝洪凯译.北京:机械工业出版社,2011:20-33.
    [72]罗伯特·J.希勒.非理性繁荣[M].北京:中国人民大学出版社,2008.
    [73]石勇,张悦.让数据说话:数据挖掘技术的商业价值及其在金融行业的应用[J].市场研究,2007,(11):80-83.
    [74]孙伟平.信息时代的社会历史观[M].南京:江苏人民出版社,2010.
    [75]唐毅,陈能华.信息的经济效益及测定[J].中国图书馆学报,2004,(6):76-78.
    [76]托马斯·H.达文波特,珍妮·G.哈里斯.数据分析竞争法-企业赢之道[M].康蓉,吴越译.北京:商务印书馆,2011.
    [77]亚当·斯密.国民财富的性质和原因的研究[M].郭大力,王亚南译.北京:商务印书馆,2009.
    [78]王书瑶.无形价值论[M].北京:东方出版社,1992.
    [79] William H·Inmon.数据仓库(原书第4版)[M].王志海等译.北京:机械工业出版社,2006.
    [80]武剑.内部评级系统的数据管理[J].中国金融电脑,2004,(11):28-32.
    [81]徐宏忠,符正平,聂广礼.基于数据挖掘的金融市场风险刻画研究[J].现代科学管理,2009,(4):97-99.
    [82]王靖雯,刘锦淼.商业银行数据仓库建设及数据服务价值[J].中国金融电脑2010,(7):17-21.
    [83]王文献.金融数据模型[M].北京:中国经济出版社,2007.
    [84]许新霞.新兴委托代理下的侵占与治理[D].武汉:武汉大学(博士学位论文),2007:
    [85]肖峰.信息的价值问题与信息论信息主义[J].学术界,2010,(2):56-63.
    [86]肖可砾熊辉.运用数据挖掘技术检测金融欺诈行为[J].金融电子化(社会科学版),2010,(8):89-90.
    [87]闫冰竹.商业银行价值管理[M].北京:中国金融出版社,2008.
    [88]杨文祥.信息资源价值论-信息文明的价值思考[M].北京:科学出版社,2007.
    [89]袁庆明.新制度经济学教程[M].北京:中国发展出版社,2011.
    [90]约瑟夫·熊彼特.资本主义、社会主义与民主[M].吴良健译.北京:商务印书馆,1999.
    [91]徐昕.西方商业银行金融创新的历程[J].金融前沿,2000,(2):21-26.
    [92]徐振东.银行家的全面风险管理-基于巴塞尔Ⅱ追求银行股东价值增值[M].北京:北京大学出版社,2010.
    [93]约翰·梅纳德凯·恩斯.就业、利息和货币通论(重译本)[M].高鸿业译.北京:商务印书馆,2011.
    [94]杨进明.使用价值的效用和效用价值[J].宁夏党校学报,2011,13(5):86-89.
    [95]杨永恒.客户关系管理:价值导向及使能技术[M].大连:东北财经大学出版社,2002.
    [96]张维迎.博弈论与信息经济学[M].上海:格致出版社,上海三联书店,上海人民出版社,2004.
    [97]郑文范.科技价值论[M].沈阳:东北大学出版社,2005:120-140.
    [98]郑国英.中国商业银行金融产品创新演化研究[D].杭州:浙江大学(博士学位论文),2009:
    [99]张嵩,黄立平.信息技术如何创造持续竞争优势—一种基于资源的观点[J].管理工程学报,2003,(3):108-110.
    [100]周竺,孙爱英.知识管理研究综述[J].中南财经政法大学学报,2005,(6):27-33.
    [101]中国人民银行.中国金融标准化报告[M].北京:中国金融出版社,2009.
    [102]中国银行业协会,普华永道.中国银行家调查报告2010[M].中国金融出版社,2010:87.
    [103]中国大陆上市银行2010年第三季度报告分析.Working Paper.德勤公司(Deloitte),2010.
    [104]朱小宗.信用风险度量模型分析及其在我国银行业的应用研究[D].武汉:武汉大学(博士学位论文),2005:
    [105]邹鹏,李一军,叶强.客户利润贡献度评价的数据挖掘方法[J].管理科学学学报,2004,7(1):53-59.
    [106]张红军.外资银行进入与监管研究[D].上海:上海交通大学(博士学位论文),2008:
    [107]张兰霞,吴国华. CRM中的客户分类管理[J].东北大学学报(社会科学版),2003,5(2):106-108.
    [108]张震,崔林立.数据挖掘技术分析及其在金融管理决策中的作用[J].广西金融研究,2007,(6):29-33.

© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号

地址:北京市海淀区学院路29号 邮编:100083

电话:办公室:(+86 10)66554848;文献借阅、咨询服务、科技查新:66554700