Upcoming SlideShare
Loading in...5




IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com

IJERA (International journal of Engineering Research and Applications) is International online, ... peer reviewed journal. For more detail or submit your article, please visit www.ijera.com



Total Views
Views on SlideShare
Embed Views



0 Embeds 0

No embeds



Upload Details

Uploaded via as Adobe PDF

Usage Rights

© All Rights Reserved

Report content

Flagged as inappropriate Flag as inappropriate
Flag as inappropriate

Select your reason for flagging this presentation as inappropriate.

  • Full Name Full Name Comment goes here.
    Are you sure you want to
    Your message goes here
Post Comment
Edit your comment

U25107111 U25107111 Document Transcript

  • S.Thiripura Sundari, Dr.A.Padmapriya / International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 www.ijera.com Vol. 2, Issue 5, September- October 2012, pp.107-111 Structure Of Customer Relationship Management Systems In Data Mining S.Thiripura Sundari*, Dr.A.Padmapriya** *(Department of Computer Science and Engineering, Alagappa University, Karaikudi-630 003 ** (Department of Computer Science and Engineering, Alagappa University, Karaikudi-630 003ABSTRACT As a young research field, data mining The center of customer becomes the inevitable choicehas made broad and significant progress. Today, of enterprise management strategy. Therefore, thedata mining is used in a vast array of areas, and profits from customer relationship has become thenumerous commercial data mining systems are blood of all enterprises, and the three basic ways toavailable. On the basis of detailed analysis of the increase profits which are obtaining new customers,existing CRM structure, a new design scheme of increasing the profitability of existing customers andcustomer relationship management systems based extending customer relationships have gained wideon data mining is presented and the design details attention.of which are illustrated in detail. II. CRM AND DATA MININGKeywords –Customer Relationship Management, Since 80s of 20th century, the applicationsData Mining. of various high technologies make it’s difficult to cut down vast majority of products’ cost. At the sameI. INTRODUCTION time, the tendency of economic globalization makes Customer Relationship Management the competition in market more intense. In such(CRM), is favored by more and more enterprises double pressure, more and more enterprises turn theirunder the impact of modern information technology. gaze to customers. Customer relationshipThere is a growth of understanding of that market management generate in this context. Gartner Groupcompetition is the competition for customer put forward a complete CRM concept in 1993. Theresources. Enterprises must rely on customers to group think that “CRM is organizing businesses byachieve profitable. In the fierce market competition, focusing on customer segmentation, it encouragesin order to maintain superiority and long-term and acts of meeting customers’ needs and achieve the linkstable development, we must attach importance to between customers and suppliers and using othercustomer relationship management. And only means to increase profits, revenue and customercontinued to gain and maintain valuable customers satisfaction. It’s a business strategy across the entireand achieve customer demand for personalized, in- enterprise.”depth excavation in order to achieve the corporation-customer win-win. This kind of customer relationship management, customer-centric business strategy, is In the market environment with high degree based on information technology. It restructures theof disturbance, the intensified competition intensity, work processes in order to give businesses betterthe highly refined products, the increasingly saturated customer communication skills, maximize customermarket, the increasingly convergence of the product profitability. Customer relationship managementquality and service characteristic, and the short typically includes the whole processes that determine,product life cycles make the customer choose more select, seek, develop and maintain their clients toample, the buyer market increasingly growing, the implement. The main objective of its management iscustomer transfer costs declined and the customer life to increase efficiency, expand markets and retaincycle shortened. Under such circumstances, how to customers.improve the customer transfer costs, extend thecustomer life cycle and maximize the customer And data mining, also known as Knowledgeprofits become problems the enterprises need to Discovery in Database, KDD, is from a largesolve. At the same time, the uncertain increase of database or data warehouse to extract people arecustomer demand, the growing trend of individuality interested in knowledge that is implicit in advanceand diversification, and the intensified changes make unknown, the potential useful information. Datathe operational risks of enterprise increased mining is data processing in a high-level process,significantly. The high market disturbance makes that which from the data sets to identify in order to modelthe business concept which regards product to represent knowledge. The so-called high-levelmanagement as the centre faces enormous challenges process is a multi-step processing, multi-stepand leads to that the relationship management with interaction between the repeated adjustments, to form 107 | P a g e
  • S.Thiripura Sundari, Dr.A.Padmapriya / International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 www.ijera.com Vol. 2, Issue 5, September- October 2012, pp.107-111a spiral process. The knowledge of mining expressesas Concepts, Rules, Regularities and other forms.CRM Data mining is from a large number of relevantcustomer data in the excavated implicit, previouslyunknown; the right business decisions have thepotential value of knowledge and rules. Technically,customer relationship management data miningsystem using infiltrated the way; you canautomatically produce some of the requiredinformation. Deeper mining are also neededenterprises statistics, decision sciences and computerscience professionals to achieve. Clustering Analysis is a widely used datamining analytical tools. After clustering, the sametypes of data together as much as possible, while theseparation of different types of data as possible. Willbe a collection of objects divided into severalcategories, each category of objects is similar, butother categories of objects are not similar. Adoptionof clustering people can identify dense and sparseregions, and thus found that the overall distributionpatterns and data among the interesting properties ofmutual relations. Such as the enterprise customerclassification, through the customer’s buyingbehavior, consumption habits, and the background toidentify the major clients, customers, and tap Fig. 1 Data Mining Basic Processpotential customers. There are many clusteringalgorithms, this means using K-means algorithm. K- 1.1 Data mining in CRM systemmeans algorithm is a specific means: for a given Data mining technology is not only thenumber of classes K, the n objects assigned to a class simple retrieval, query and transfer faced to specialK to go, making within-class similarity between database, it also should do microcosmic andobjects the most, while the similarity between the macroscopically statistics, analysis, synthesis andsmallest class. reasoning to guide the solving of practical problems, find the relationship between events, and even use theIII. DATA MINING IN CRM SYSTEM existing data to predict future activities. In order to Data mining uses some mature algorithms achieve data mining, now a number of software toolsand technologies in artificial intelligence, such as have been developed and formed many aspects of aartificial neural networks, genetic algorithms, number of products in the customer relationshipdecision tree, neighboring search methods, rule-based management, such as customer evaluation andreasoning and fuzzy logic. According to the different subdivision, customer behavior analysis, customerfunctions, the analyzed methods of data mining can communication and personalized services. The actionbe divided into the following types: classification, of data mining in CRM is represented as thevaluation, correlated analysis and clustering. following aspects: Data mining technology is not only the 1.1.1 Customer characteristics multi-simple retrieval, query and transfer faced to special dimensional analysisdatabase, it also should do microcosmic and It refers to analyzing the customermacroscopically statistics, analysis, synthesis and characteristic demand. The customer attributereasoning to guide the solving of practical problems, description should include address, age, sex, income,find the relationship between events, and even use the occupation, education level, and many other fields,existing data to predict future activities. and can be carried multi-dimensional combination The basic data mining process is composed analysis and quickly presented with the list and theby the following steps number of customers which accord with the conditions. For example: customer subdivision model is an effective tool of typical customer identification and analysis and the compendia data provides the basis for customer categorization and subdivision. The course, a subdivision standard must be defined firstly, for example, according to the profit 108 | P a g e
  • S.Thiripura Sundari, Dr.A.Padmapriya / International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 www.ijera.com Vol. 2, Issue 5, September- October 2012, pp.107-111contribution of the customers they can be subdividedinto high-profit customer groups, the profitablecustomer groups, profit margin customer groups,non-profit customer groups and deficit customergroups, which separately corresponding to goldcustomer, emphasis customer, hypo-emphasiscustomer, common customer and deficit customer.1.1.2 Customer behavior analysis It refers to analyzing the consumingbehavior of certain customer group combiningcustomer information. And according to differentconsuming behaviors changes, individuationmarketing strategies will be established and theemphasis customer or the customer with the trend ofloss will be selected. For example: through the setting ofstandards users automatically monitor some basicindicators and data of operation run and timelycompare them with conventional, standard data, Fig. 2 CRM Structure Based on Data Miningwhen more than a certain percentage the abnormalwarning will be advanced. Many customer behavior The whole system can be divided into threechanges may mean that customers have "left" layers: the interfacial layer, the functional layer andtendency, therefore, their behaviors should be the layer of support. The interfacial layer is theidentified in time and the efforts should be made interface to interact with users, access or transmitbefore the customer decision. information, and it provides intuitive, easy-to-use1.1.3 Customer structure analysis interface for users to access to the necessary Through the statistical analysis (a particular information conveniently; the functional layer isunit time interval for statistics) of the various types of composed by the subsystem with basic function inIt refers to the analysis of customer contact and CRM, each subsystem as well as includes a numbercustomer service. According to the analyzing result of operations which form a operational layer; and theof customer concerns and customer tendency, layer of support includes database managementunderstanding and mastering their needs and system and operating system.providing the communication content they interested 1.3 Functional Design of CRM Systemin the most appropriate time through their preferred The functional structure of the system ischannels, which can enhance the attractiveness of the designed in accordance with the top-down principle,customers. which is gradually target system decomposition At the same time it can improve the process; it divides the whole system into severalsubordinate institution capacity of differentiated subsystems and enables them to complete theservices, achieve the customer-focused product functions of the various subsystems, the systemdevelopment and optimization, distribution channel functional modules are shown in Figure 3management and customer relationship optimization,and improve the overall marketing and customerservice levels.1.1.4 Sales analysis and sales forecast It includes the analysis according toproducts, sales promotions effect, sales channels andmethods. At the same time, it also analyzes thedifferent effects of different customers to businessbenefit, analyzes the effects of customer behavior tobusiness benefit, this makes the relationship betweenbusiness and customer.1.2 CRM system design based on data mining1.2.1 CRM system structure Based on the analysis of existing CRMstructure and according to the analysis of CRM coreidea, here a CRM structure based on data mining is Fig. 3 Functional Design of CRM Systembuilt, as shown in Figure 2 109 | P a g e View slide
  • S.Thiripura Sundari, Dr.A.Padmapriya / International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 www.ijera.com Vol. 2, Issue 5, September- October 2012, pp.107-1111.3.1 CR Clustering Analysis cross-selling opportunities, provide more CR clustering analysis module subdivides comprehensive services to customers andthe customers according to customer values. Because consequently bring greater benefits to enterprises.that for each enterprise the customer values standardsare different, so it is needed to carry out customer 1.3.5 Customer loss analysisclustering subdivision for the existing customers of Through the observation and analysis of thethe enterprises, set the corresponding customer level customer historical transactions, enterprise endowsand give class marker for the customers according to customer relationship management modules thethe customer value by using the clustering result. function of customer warning abnormal behaviors. There area total of five category markers, The system makes the warning signs to the potentialthat is, high-value customers, customers with the loss of customers through automatically checking themost growth, ordinary customers, negative value customer transaction data. And the customer losscustomers and new customers. prediction analysis can help enterprises to find the lost customers and then adopt measures to retain1.3.2 CR value judgment them According to the result of the customer .clustering analysis, the CR value judgment uses C4.5 1.3.6 Data managementdecision tree algorithm to establish classification The data management is to maintain andmodel and describe the specific characteristics of manage the customer information, transactionvarious types of customers. And in accordance with information, rule information and other related data,the different characteristics of various types of and it enables operators to quickly find or modify thecustomers it also may adopt corresponding required relevant information.processing means, which guides enterprises toallocate resources to the valuable customers in the 1.4 DATA MINING IMPLEMENTATIONaspects of marketing, sales, services, gives special The mining can be implemented in twosales promotions for the valuable customers, provides steps: the first step, selecting the average customermore personalized service to enable enterprises to purchase sum and purchase number, and using theobtain the maximum return on minimum investment. method of clustering for the classification of customers, thus each customer has an affirmed1.3.3 Customer structure analysis category; second step, using decision tree model to Through the statistical analysis (a particular build decision tree for customers, to do furtherunit time interval for statistics) of the various types of classification analysis on the customercustomer characteristics, customer structure analysis characteristics.helps the marketing manager to make marketingdecisions; and through the vertical comparison of the IV. CONCLUSIONcustomer structure, it provides an important basis for Many companies increasingly use datathe management work of the customer relationship mining for customer relationship management. Itevaluation and adjustment. helps provide more customized, personal service The activities the customer relationship addressing individual customer’s needs, in lieu ofmanagement concerned are four: access to new mass marketing. As a chain reaction, this will resultcustomers, keep old customers, customer structure in substantial cost savings for companies. Theupgrading and the overall customer profitability customers also will benefit to be notified of offersimprovement. And according to these, the customer that are actually of interest, resulting in less waste ofstructure analysis regards the rate of new customers, personal time and greater satisfaction.customer retention, customer promotion rates and To enterprises, CRM is not technology, butcustomer profitability as the four analyzing goals a management style, but also a business strategy. It is difficult for enterprise to meet the customer specific1.3.4 Customer behavior analysis module needs if it only implements a generic CRM solution. Customer behavior analysis module mainly This will require that the enterprises can implementanalyzes the customer satisfaction, customer loyalty, different solutions step-by-step and ultimately formcustomer responsiveness and the cross-selling. an overall CRM solution, and can achieveMaintaining long-term customer satisfaction and personalized management and implementation. Atcustomer loyalty contributes to the establishment of the same time enterprises also need to continuouslycustomer relations and ultimately improve the improve the CRM system to better manage thecompany long-term profitability. Customer customers. It can be believed that the CRM systemresponsiveness analysis can effectively guide the will become the essential system for enterprisesales and marketing behavior, improve the past sales survival and development, and the CRM system willwithout goal and reduce the cost of sales. be further mature with the development of It also can do correlation analysis for the technology and management thinking to play a moreexisting customer purchasing behavior data, find the 110 | P a g e View slide
  • S.Thiripura Sundari, Dr.A.Padmapriya / International Journal of Engineering Research and Applications (IJERA) ISSN: 2248-9622 www.ijera.com Vol. 2, Issue 5, September- October 2012, pp.107-111significant effect role in the whole development of BIOGRAPHYthe community. S.Thiripura Sundari, a very enthusiastic andREFERENCES energetic scholar in M.Phil degree in Computer [1] Han, J. and Kamber, M. Data Mining : Science. Her research interest is in the field of data Concept and Techniques, Morgan mining. It will further be enhanced in future. She is Kaufmann Publisher: San Francisco, USA, equipping herself to that by attending National 2001 Conferences and by publishing papers in [2] M.J.A. Berry and G.Linoff. Data Mining International Journals. Techniques: For Marketing, sales, and Customer Relationship Mnagement. John Dr.A.Padmapriya is the Assistant Professor in Wiley & Sons, 2004. the Department of Computer Science and [3] M.J.A. Berry and G.Linoff. Mastering Data Engineering, Alagappa University, Karaikudi. She Mining: The Art and Science of Customer has been a member of IACSIT. She has presented a Relationship Management. John Wiley & number of papers in both National and International Sons,1999 Conferences. [4] Weiser Mark, “The Computer for the Twenty-first Century”, Scientific American, 1991, 265(3): 94-100. [5] Magnus Blomstrom, Kokko, “Human Capital and Inward FDI”, NBER working paper, 2003, 1 [6] Krishma K, Murty M. N, “Genetic k-means algorithm”,IEEE Tram on System, Man, and Cybernetics: Part B,1999, 29(3):433-439. [7] Jin Hong, Zhou Yuan-hua, “Video Disposing Technology Basing on Content Searching”, Journal of Image and Graphics, 2000, 5(4):276-282. [8] H Kargupta, B Park, et al, “Mob Mine: Monitoring the Stock Market from a PDA”, ACM SIGKDD Explorations, 2002, 3(2): 37- 46. [9] D Terry, D Goldberg, D Nichols, et al, “Continuous Queries over Append-only Databases”, Proceedings of the ACM SIGMOD Int’l Con.f on Management of Data, Madison: ACM Press, 2002. 1-26. [10] JS Vitter, “Random Sampling with a Reservoir”, ACM Trans. on mathematical software, 1985, 11(1): 37-57. 111 | P a g e