You are on page 1of 54



Nesibe ŞAHİN
Ahmet ÖNCE

June 2004



Nesibe ŞAHİN
Ahmet ÖNCE

A thesis submitted to

The Industrial Engineering Department


Fatih University

June 2004
Istanbul, Turkey



Nesibe ŞAHİN
Ahmet ÖNCE

Bachelor Thesis - Industrial Engineering
June 2004

Supervisor: Ass. Prof. Erkan Topal


CRM and applications of CRM in some sectors are examined. Information about
data analysis and data mining techniques are gathered. Simulated three-month-data of
calling times of a GSM operator is evaluated, most used tariffs according to Pareto
analysis are determined and focused on these tariffs. Statistical distributions of calling
times of these tariffs and central tendency values are determined. These three month
data is compared in between. After that, the cities that use this GSM operator mostly are
considered. The distributions of calling times of these cities’ most used tariffs are
determined. These data is evaluated and reports that cover all of these evaluations are
prepared. According to these reports, existing conditions are determined, problem in the
current system are defined and proposals to improve this system are done.

Keywords: Customer Relationship Management, CRM, Data Mining, GSM, Calling
Times, Statistical Distributions.



Nesibe ŞAHİN
Ahmet ÖNCE

Lisans Tezi – Endüstri Mühendisliği
Haziran 2004

Tez Yöneticisi: Yard. Doç. Erkan Topal


Müşteri ilişkileri Yönetimi(CRM) ve bazı sektörlerdeki CRM uygulamaları
incelendi. Veri analizi ve veri değerlendirmesi ile ilgili bilgi edinildi. Aslına uygun
şekilde modellenmiş bir GSM şirketinin üç aylık arama süreleri değerlendirildi, en çok
kullanılan tarifeleer Pareto analizine gore belirlendi. Bu tarifelerdeki konuşma
sürelerinin istatiksel dağılımları ve merkezi eğilim değerleri belirlendi. Bu üç aylık data
kendi aralarında kıyaslandı. Daha sonra, bu GSM operatörünün en çok kullanıldığı
şehirler tespit edildi. Bu veriler değerlendirildi ve bütün bu değerlendirmeleri kapsayan
raporlar hazırlandı. Bu raporlara göre; varolan durum tespit edildi, şimdiki sistemin
problemleri belirlendi ve sistemi geliştirmek için önerilerde bulunuldu.

Anahtar Kelimeler: Müşteri ilişkileri Yönetimi, CRM , GSM, Arama Süreleri,
İstatistik Dağılımlar








..............................................45 APPENDIX C…………………………………………………………………………........iii TABLE OF CONTENTS..........1 WHAT IS DATA MINING?..........................................................ii A CRM APPLICATION IN GSM SECTOR................................ TABLE OF CONTENTS A CRM APPLICATION IN GSM SECTOR.......93 APPENDIX D……………………………………………………………………….........................44 APPENDIX B…………………………………………………………………………..100 APPENDIX E………………………………………………………………………............103 REFERENCES………………………………………………………………………104 vii .............................................vii 3........25 APPENDIX A…………………………………………………………………………..................................................................



The personal relationship between merchant and customer became a thing of the past. moving to the supplier who provided the desired object at lowest cost or with the most features. remained loyal to the store and made repeated purchases. customers became fickle. Its objective is to return to the world of personal marketing. market to each customer individually. CHAPTER 1 INTRODUCTION 1. previous purchases. information about a customer (e. The last several years saw the rise of Customer Relationship Management (abbreviated CRM) as an important business approach. Rather than market to a mass of people or firms. The customer. in turn. The concept itself is relatively simple. This idyllic customer relationship disappeared as the nation grew. the mall. the population moved from the farm communities to large urban areas. needs.. people went to their neighborhood general store to purchase goods. Although prices were lower and goods more uniform in quality. the consumer became mobile. As a result.1 CUSTOMER RELATIONSHIP MANAGEMENT (CRM) Before the advent of the supermarket. In this one-to-one approach. the relationship between the customer and the merchant became nameless and faceless. This approach is made possible by advances in information technology.g. and supermarkets and department stores were established to achieve economies of scale through mass marketing. 1 . and the automobile. The proprietor and the small staff recognized the customer by name and knew the customer's preferences and wants. preferences and wants) is used to frame offers that are more likely to be accepted.

customer services. human resource management. manufacturing management. 2 . field sales. CRM requires organizational and business level approaches – which are customer centric – to doing business rather than a simple marketing strategy. Management is a broader concept than marketing because it covers marketing management. and field service) required to contact customers directly or indirectly. sales management. CRM involves all of the corporate functions (marketing. not Customer Relationship Marketing. Remember that CRM is an abbreviation for Customer Relationship Management. and research and development management. The term “touch points” is used in CRM to refer to the many ways in which customers and firms interact. Thus. manufacturing. service management.

targets. 1) Sales Force Automation Capabilities Contact Management: Maintain customer information and contact histories for existing customers. Followings is the range to sales force automation capabilities currently available. May include point in the sales cycle and in the customer’s replenishment cycle. Sales Force Automation (SFA) and 2.1 HISTORY OF CRM MARKET Before 1993. CRM included two major markets: 1. SFA’s meaning expanded to include opportunity management that is supporting sales methodologies and interconnection with other functions of the company such as production. Sales Force Automation was initially designed to support salespersons in managing their touch points and to provide them with event calendars about their customers. and projections Opportunity Management: Manage leads and potential leads for new customers Order Management: Obtain online quotes and transform inquiries into orders 3 . CHAPTER 2 CUSTOMER RELATIONSHIP MANAGEMENT 2. Customer Services (CS). Activity Management: Provide calendar and scheduling for individual sales people Communication Management: Communicate via E-mail and fax Forecasting: Assist with future sales goals.

with the right parts. Document Management: Develop and retrieve standard and customizable management reports and presentation documents Sales Analysis: Analyze sales data Product Configuration: Assemble alternate product specifications and pricing Marketing Encyclopedia: Provide updated information about products. and track problem reports • Provide updates. and time associated with service orders • View customer history • Search for proven solutions Help Desk Management • Solve the problem by searching the existing knowledge base • Initiate. promotions. as well as soft information about individuals (e. and product development. influence on buying decisions) and information about competitors Compared to SFA. expenses. Field Service Management • Allocate. Customer Service (CS) is an after sales activity to satisfy customers. prices. 2) Customer Services Capabilities Call Center Management • Provide automated. quality control. at the right time • Log materials. field service management. schedule. customer services include call center management. and new versions 4 . and dispatch the right people. and help desk management.g. modify. By providing fast and accurate answers to customers. a company can save cost and increase customer loyalty and revenue.. As mentioned below. patches. The goal of Customer Service is to resolve internal and external customer problems quickly and effectively. end-to-end call routing and tracking • Capture customer feedback information for performance measurement.

• Vantive was bought by Peoplesoft in 1999. SAP and Oracle Corporation were introducing new application to the market based on their software development capabilities. Siebel Systems Inc. Vantive (PeopleSoft) and Clarify Inc. was the market leader with a 35% share. Vantive and Clarify were the major vendors. Since then.1. Scopus. and Aurum. Inc. and Clarify (now Nortel). which in turn was acquired by Invensys plc in July 2000. 2. In 1998. In the CS area. Brock Control changed its name to Firstwave Technologies.Today.piphany. including: • Sales Force Automation (SFA). Trilogy.. Sales Technologies. Recent entrants offering Web applications and services include Silknet Software. things also changed rather rapidly: • Siebel merged with Scopus in 1995 and dominated the consolidated CRM market with 68% market share. 5 . • Sales and Marketing Management (SMM). However. and Contact & Activity Management. CRM includes all customer-facing applications. to provide pharmaceutical and healthcare industry relationship management service. and netDialog. • Clarify was bought by Nortel in 1999. E. the CRM market was divided by Siebel. and Oracle (in that order) plus fewer than 20 other companies with small market shares.1 Major Vendors The major vendors changed over time. In 1993. Aurum was merged into Baan. • Customer Service (CS). In 1998. At the beginning of 2000. Vantive (now PeopleSoft). Sales Technologies merged with Walsh International and now is consolidated into SYNAVANT Inc. the leaders of SFA were Brock Control. (Nortel) followed.

To deliver that vision. 6 . development. people. marketing. the aim of a CRM strategy is to maximize profitable relationships with customers by increasing the value of the relationship for both the vendor and the customer. “It’s a business approach that builds customer loyalty and retention.” Jim Goldfinger.” Vic Guerrieri. For most companies. maintenance and optimization of the long term mutually valuable relationships between customers and organizations. “Managing profitable relationships. business development associate at Oncontact Software. It entails acquiring and deploying knowledge about customers and using this information across the various customer touch points to increase revenue and achieve cost reduction through operational efficiencies. vice president of CRM strategy at PeopleSoft.” Jon Wurfl. organizational and technical change whereby a company seeks to better manage its enterprise around its customer behaviors. you need a CRM strategy which gives shape to your sales.2 MISCELLANEOUS DEFINITIONS OF CRM “CRM is a business strategy comprised of process. technology. customer service and data analysis activities.” “The art of creating e-dialogues.” Margaret Gerstenkorn. Successful CRM focuses on understanding the needs and desires of the consumer and is achieved by placing these needs at the heart of business by integrating them with the organization’s strategy.” “CRM is a business philosophy which provides a vision for the way your company wants to deal with your customers.” “CRM is the establishment. and business processes.2. “Conquering barriers that prevent customers and companies from knowing each other.” John O’Connell. vice president of sales at Remedy. director of CRM communications at SAP. chairman and CEO of Staffware. “Sensing and responding to customers in real-time.

” CRM consists of three components: • customer. and longer periods of retention. “CRM is a business strategy that goes beyond increasing transaction volume. It’s not a one-off. To achieve CRM. and improve employee morale. technologies. and • management. “CRM is a company’s ability to continuously maximize the value of its customer franchise by effectively allocating scarce resources to specific customers or customer segments in those areas viewed as having a significant impact on the profit-impacting behaviors of customers or segments. Thus. revenue. CRM tries to achieve a ‘single integrated view of customers’ and a ‘customer- centric approach’. It should help sales. raise productivity.” Cap Gemini Ernst & Young. Its objectives are to increase profitability. CRM is primarily a strategic business and process issue rather than a technical issue. a company wide set of tools.” Barton Goldenberg. and customer service. Successful application of CRM leads to economically efficient acquisition of additional customers and relationships. and procedures promote the relationship with the customer to increase sales. is always scarce because customers are knowledgeable and the competition is fierce. improvement in relationship profitability. who provides more profit with less resource. but a complete approach that coordinates customer-facing operations like sales. Sometimes it is difficult to distinguish who is the real customer because the buying 7 . • relationship. I define CRM as a business approach that integrates PPT (people. “Our industry has not done a good enough job to make that value proposition clear. Customer: The customer is the only source of the company’s present profit and future growth. process and technology) to maximize relations with all customers. a good customer. founder and president of ISM. and customer satisfaction. However. marketing. the three key dimensions of value of customer franchises.

CRM can be thought of as a marketing approach that is based on customer information. • Self service applications. • Bill presentation. Specific software to support the management process involves: • Field service. the buying pattern for airline tickets depends on whether a person buys the ticket for their family vacation or a business trip. their buying behavior is highly situational. CRM required a comprehensive change in the organization and its people. The relationship can be short- term or long-term. and repeating or one-time. • E-commerce ordering. Customer lifetime value (CLV) is a tool for measuring this relationship. • Catalog management. CRM involves managing this relationship so it is profitable and mutually beneficial. All of these techniques. continuous or discrete. processes and procedures are designed to promote and facilitate the sales and marketing functions. Information technologies can provide the abilities to distinguish and manage customers. Relationship can be attitudinal or behavioral. Management: CRM is not an activity only within a marketing department. Rather it involves continuous corporate change in culture and processes. • Marketing programs. The customer information collected is transformed into corporate knowledge that leads to activities that take advantage of the information and of market opportunities. 8 . and • Analysis applications.decision is frequently a collaborative activity among participants of the decision-making process. For example. Relationship: The relationship between a company and its customers involves continuous bi-directional communication and interaction. Even though customers have a positive attitude towards the company and its products.

From a purely economic point of view. 2 to 3 calls to sell an existing customer. Thus. Another driver is the change introduced by electronic commerce. • A typical dissatisfied customer tells 8 to 10 people about his or her experience. the costs to market to existing Web customers is $6. Thus. Rather than the customer dealing with a salesperson either in a brick and mortar location or on the phone. firms learned that it is less costly to retain a customer than to find a new one. • In industrial sales. the prime approach to attracting new customers was through media and mail advertising about what the firm has to offer. firms do not have the luxury of someone with sales skills to convince the customer. For example. it is assumed that 20% of a company's customers generate 80% of its profits. in electronic commerce the customer remains in front of their computer at home or in the office. This advertising approach is scattershot. the typical response rate from a general mailing is about 2%.3. • A 5% increase in retaining existing customers translates into 25% or more increase in profitability. Whereas normally it takes effort for the customer to move to a 9 . • It is 5 to 10 times more expensive to acquire a new customer than obtain repeat business from an existing customer. reaching many people including current customers and people who would never become customers. according to the Boston Consulting Group.000 responses on average. mailing a million copies of an advertisement yields only 20. it takes an average of 8 to 10 physical calls in person to sell a new customer.1 Reasons For Adopting CRM: The Business Drivers Competition for customers is intense. In the past.2. For example. The oft- quoted statistics go something like this: • By Pareto’s Principle.80 compared to $34 to acquire a new Web customers.3 DRIVERS FOR CRM APPLICATION 2.

competitor’s physical location or dial another 1-800 number.2 Cost Goals Major cost goals of CRM include: • Increase revenue growth through customer satisfaction. To increase customer satisfaction • Make the customer’s experience so pleasant that the customer returns to you for the next purchase. • Automate the call center so that representatives have direct access to customer history and preferences and therefore can cross-sell. • Manage customer relationships rather than manage products (a change in marketing). • Use web applications to decrease the number of direct sales people and distribution channels needed. To reduce cost of sales and distribution • Target advertising to customers to increase the probability that an offer is accepted. To minimize customer support costs • Make information available to customer service representatives so they can answer any query. 1. • Reduce costs of sales and distribution • Minimize customer support costs The following examples illustrate tactics to achieve these goals. 2. To increase revenue growth • Increase share of wallet by cross-selling. in electronic commerce firms face an environment in which competitors are only a few clicks away.3. 2. 4. 3. 10 .

hardware. Interpolated values are shaded. personnel. mailing. some of the values shown were obtained by taking the forecaster’s growth rate and then interpolating.4. Not all values shown in Table 1 are forecasts. 1 Estimated CRM Market Size Figure 2.g. These illustrations show forecasts made in the 1997 to 2000 period by a number of industry research groups.. 1: CRM Market Size 11 . it is not possible to tell which expenditures (e. software.4 THE CRM INDUSTRY 2. call centers …) and which revenues are included in the numbers shown. Therefore.1 Size Of The CRM Industry Estimates of the size of the CRM industry are shown in Table1 and plotted in Figure 1. Table 2. It is important to realize that the forecasters generally did not specify what they included in their estimates.2.

is that the market is growing and is multibillion. For example. 12 . and PeopleSoft) acquire. Starting in late 1998. Clearly the forecasts shown vary significantly as they reach the out years because they are based on different assumptions of the size of the current market at the time of the forecast and the growth rate inferred from the numbers presented. eGain was in e-mail management. Davox moved into customer contact management.2 Vendors A few years ago. Siebel. and partner their CRM application for ERP functionality. 2. technology vendors had their own specialties. • Front-End Application Some companies started with front-end solutions such as personal information management system (PIMS). Remedy was in helpdesk systems. build. Davox was in call center systems. and BroadVision is trying to integrate backward with ERP. For example. and Remedy are in this category. Siebel says it can do everything. there is no specific boundary of vendors. Table 2 lists some of the major categories and players. and BroadVision was in the front-end application area. All vendors are trying to expand their products over the entire CRM area. Siebel was in sales force automation. Today. Baan (now Invensys plc). BroadVision. many of the larger players acquired or merged with mid-sized companies to allow them to offer full service across the entire CRM “sandbox”. with the fast development of e-business. however. The important point.4. Most of CRM vendors came from two different origins: • Back-End Application Traditional ERP vendors (SAP AG. Oracle Corporation.

The basic questions that CRM tries to answer are: 1. customers were not kept loyal by the discount programs and the one-time promotions that were used in the database-marketing programs.5 INFORMATION TECHNOLOGIES FOR CRM CRM differs from the previous method of database marketing in that the database marketing technique tried to sell more products to the customer for less cost. The database marketing approach is highly company centric. very difficult to obtain or buy. What is the benefit of the customer? 2. Customer loyalty is. 2: The Major CRM Vendors 2.Table 2. How can we add the customer’s value? 13 . The CRM approach is customer-centric. indeed. However. This approach focuses on the long-term relationship with the customers by providing the customer benefits and values from the customer’s point of view rather than based on what the company wants to sell.

Through the personalization process. the customer’s long- term profitability and relationship to the company is important. for CRM. and interactions over time. differentiate. and for the information technologies used in CRM. and customize for individual customer needs. Jeff Bezos. “Our vision is that if we have 20 million customers. 1. then we should have 20 million stores. Customization / Personalization “Treat each customer uniquely” is the motto of the entire CRM process. the company must know or identify the customer through marketing channels. Customer Differentiation Each customer has their own lifetime value from the company's point of view and each customer imposes unique demands and requirements for the company. Although some argue that IT has a small role in CRM.Four basic tasks are required to achieve the basic goals of CRM. 14 . the company needs to learn about the customer continually. interact with. Customer Identification To serve or provide value to the customer. the CEO of Amazon. for traditional mass marketing.5. each of the four key CRM tasks depends heavily on information technologies and systems. for the goals. 2. Keeping track of customer behavior and needs is an important task of a CRM program. 3.1 IT Factors of CRM Traditional (mass) marketing doesn’t need to use information technologies extensively because there is no need to distinguish. the company can increase customer loyalty. Table 3 shows this relationship for the marketing processes. Customer Interaction Customer demands change over time. 2. Therefore. From a CRM” The automation of personalization is being made feasible by information technologies. said. transactions. 4.

More than 69% of the companies surveyed spent less than $5 million.1% of company revenue. the average total investment in CRM of 300 U.S. and application requirements. the implementation cost of CRM depends on the industry. the average implementation cost of CRM can be between $15. According to GartnerGroup.000 and $35.1 million. 3: IT Factors in CRM 2. and more than 13% of the companies spent over $10 million. As shown in Tables 4 and 5.Table 2.000 per user in a three-year project. 15 . and Europe companies was $3. project size. Average implementation time for an ERP system is 23 months and the cost of ownership over the first 2 years is from 0.6 RETURN ON INVESTMENT OF IMPLEMENTATION 2. based on GartnerGroup data.6.1 Cost And Time The 1999 Cap Gemini and IDC survey also found that. The cost of implementing a CRM system is easily double the Enterprise Resource Planning (ERP) implementation cost.4% to 1.

To obtain all of these benefits.6. 4: Annual CRM Expenses (in $million) Table 2. CRM is composed of four continuous processes. customer differentiation.Table 2. customer identification. marketing. and service functions need to work together. customization. 5: Cost Allocations 2. Each process provides distinctive benefits to the organization. sales. The benefits are shown in Table 6.2 Benefits The principal benefits of CRM are to • Improve the organization’s ability to retain and acquire customers • Maximize the lifetime value of each customer (share of wallet) • Improve service without increasing cost of service. 16 . customer interaction.

2. To be successful. based on a survey of more than 500 executives in six industries (communications. sales. More than 57% of CEOs in another survey with 191 respondents believe that the major objective of CRM is customer satisfaction and retention. process and technology. customer service and field support — through the integration of people.3 CRM: Commitment To Customer & Shareholder Value Customer relationship management (CRM) is that part of an enterprise’s business strategy that enables the entire enterprise to understand. Another 17% said it is designed to increase cross selling and up selling. 17 . CRM is a comprehensive strategy that integrates all areas of business that touch the customer – though mainly. electronics/high-tech. 6: Benefits of CRM project Anderson Consulting. anticipate and manage the needs of any current and potential customers. believes that a 10% improvement of overall CRM capabilities can add up to $35 million benefits to a $1 billion business unit. CRM requires acquiring and distributing knowledge about one’s customers across the enterprise. it is limited to marketing. or even an application or a process. chemicals. business processes and key technologies are required to optimize CRM strategies.Table 2. Obviously. Ideally. CRM is not an event or a technology. revenue and profits with customer satisfaction.6. pharmaceuticals. to balance costs. forest products and retail).

and communication with. Such action implies allocating scarce resources to provide a seamless.In sum. CRM is the use of this data to improve efficiencies and effectiveness in marketing. CRM requires a large amount of initial investment in hardware and software without any immediate cost saving or revenue improvement. or fast solution. Rather. 2. The benefits of CRM need to be measured on a long-term basis. o Technologically. However.7 PRINCIPLES OF CRM 18 . A survey of 300 companies conducted at a CRM conference concluded that CRM is not a cheap. 2. high-quality experience for a company’s most valuable customers.6. CRM is based on the use of data mining to identify customer preferences and behavior. CRM is four things that provide competitive advantage to the enterprise: o Organizationally. o CRM is a commitment to drive customer satisfaction and shareholder satisfaction simultaneously. sales and support.4 ROI of CRM Project It necessary to wait-and-see to determine the Return On Investment (ROI) of CRM since CRM does not bring any direct monetary benefits after implementation. o In business processes. easy. the successful third can obtain up to a 75 % return on investment. CRM is a strategic focus on the behavior of. CRM is designed to build long-term relationships with customers and to generate long-term benefits through increased customer satisfaction and retention. More than two-thirds of CRM projects end in failure. and shedding the least desirable customers. the customer.

the worst customers should be dropped. 2. CRM is based on philosophy of personalization. CRM deals with large amounts of customer data through various touch points and communication channels. 19 . The personalization process in CRM requires identification of each individual customer and collections of demographic and behavioral data. a company can allocate its limited resources to obtain better returns. The individual firm is thus caught in an ethical dilemma.8 CRM ISSUES 2. personalization. it is the very information that most customers consider personal and private. yet in doing so it treads at and beyond the bounds of personal privacy. Personalization means the content and services to customer should be designed based on customer preferences and behavior.8. a company needs to sustain relationships with the customer. Through differentiation.1 Customer Privacy Customer privacy is an important issue in CRM. Yet. The overall processes and applications of CRM are based on the following basic principles.remember customers and treat them individually. It wants to collect as much information as possible about each customer to further its sales. The best customers deserve the most customer care. In summary. • Select “Good” Customer instead of “Bad” Customer based on Lifetime Value Find and keep the right customers who generate the most profits.’ Personalization creates convenience to the customer and increases the cost of changing vendors. Continuous contacts with the customer – especially when designed to meet customer preferences – can create customer loyalty. and lifetime value are the main principles of CRM implementation. • Acquire and Retain Customer Loyalty through Personal Relationship Once personalization takes place. • Treat Customer Individually. loyalty.

Many small companies merge together to compete with large vendor. technologies. Providing personalized service to customer is a way to satisfy customers who provided their personal information. CRM is one of the busiest industries which occurs frequent merger and acquisition. Still it is unclear and undetermined what extent of customer privacy should be protected and shouldn’t be used. and understanding of CRM are still in its early adapter stage.2 Technical Immaturity The concept. • Customer data should be protected from unauthorized usage.8. Most of the CRM technologies are immature and the typical implementation costs and time are long enough to frustrate potential users. each has different implementation requirements to achieve the customer’s expectations. and public policies around the world. Privacy issues are not simple. legal regulations. There are overwhelming customer concerns. All of these efforts are designed to build trust between the company and its customers. • The customer should be notified their personal information is collected and will be used for specific purposes. Due to these frequent merger and acquisition. Large companies such as PeopleSoft acquired small vendor to enter this ‘hot’ CRM market. Some companies provide ‘customer consent form’ to ask the customer to agree to information collection and usage. Many software and hardware vendors sell themselves as complete CRM solution providers but there is little standardized technologies and protocols for CRM implementation in the market. the stable technical support from the 20 . • The customer should be allowed to access their information and correct it. but four basic rules might be considered. Even the scope and extent of ‘what CRM includes’ differ from vendor to vendor. • The customer should be able to decline to be tracked. 2.

Com When you try to buy something from Amazon. believes the Internet store of the future should be able to guess what the customer wants to buy before the customer knows. CDs. Often these technical immaturities or unstable conditions are combined with the customer requirements which are frequently unclear and lead the project failure. which stores personal information such as credit card number and shipping address.9. but the process may be long and painful. These technical immaturities may be overcome over simplifies the customer buying process. 2. He wants to make Amazon. Amazon. compared with 3 to 5 percent for other ebusiness retailers. Amazon. the founder of Amazon. Sometimes a customer buys additional products because of this information. the company will support a ‘Welcome to Recommendations’ Web page. and low price lead customer loyalty and long-term relationship of Dell 21 . The personalized Web pages. Amazon.1 “Customers who bought this item also bought these items.” If you have any previous purchasing experience with Amazon. Like the corner merchant of old. Vendors publish new version – maybe more integrated software – of CRM software as frequently as they can and customers should pay for that. and other assembles large amounts of information on individual customer buying habits and personal information. Through its ‘1-Click’ system. you can see the following statement. vast selection of products.9 CASE STUDIES recommends Web site that smart and that Jeff Bezos. Based on a customer’s previous purchases and Web surfing More than 20 million people have purchased at Amazon. becomes rare. The percentage of returning customers is about 15 to 25 percent.

Dell developed ‘Premier Dell. the customer is routed to a more skilled contact. All advertising 22 . These personalized services also provide related information and make software downloads available. the company does not have current information about many of its customers. the mobility guarantee. 2. and order management. Premier pages support online purchasing. a call center provides technical assistance at multiple levels. standard management. As a result. Since 1983. Volkswagen developed services such as service guarantee. However. such as education. government. and customer satisfaction.7 years). In addition. and home. customer expectations. which is on the side of the computer. all of the decision-making processes are based on the ‘Voice of Customer.3 Volkswagen Volkswagen AG is the largest automobile maker in Europe. the user can contact the Dell Web site directly and get personalized services by using the customer system service tag number. the company started its ‘Customer Come First’ marketing strategy. Dell is organized by customer segment. large business. Under this strategy. small business. the company is well informed about its customers and heavily depends on this information. More than 36 million vehicles carry on their logo. instead of by product lines. Customer forums and focus group are used to hear the customer voice. the customer club. The individual customer can make his/her system unique and obtain it directly from the company. asset management.’ The company carefully monitored their response to advertisements. they lose contact with the car owner after the first change of ownership (after an average 3. Like other automobile manufacturers. Dell Computers has operated on two simple business ideas: sell computers direct to individual customers and manufacture computers based on the customer’s order. In 1988.9. price quotes. and product support. the emergency plan. If the first level technician cannot resolve the problem. and toll-free service phone. If the system has a’ that covers entire processes of computer ownership: purchasing.

The bank contacts you regularly by sending you your monthly statement. This allows the company to obtain useful information such as lifestyle. bonus point programs. It was the first bank which started 24-hour phone banking service and opened branches in the local supermarket and Starbucks coffee house. once you open your account in a specific bank. Every contact points with a customer gives the company more information about the customer. in the auto industry. In the new system. You can change your oil or maintain your car with different service station. so the company can constantly improve the quality and value of the customer database. They had to log on to several different system to obtain the information and do the transactions requested. Wells Fargo always tried to provide more touch points to its customers and a one-stop shopping environment. You may write checks more frequently.4 Wells Fargo Banking differs from other industries because the average relationship between customer and bank lasts much longer on the. the service agent can access all required information by using the customer’s social security number instead 23 .9. and withdraw money. have direct deposit. 2. Wells Fargo tried to integrate all of its back-end customer information into its Customer Relationship System. Customer service agents found it difficult to integrate customer information when they received a request to transfer from one account to another. customer information was managed by several different backend system. Previously. and Volkswagen magazine. The company maintains a central database to provide club card. are designed toward two-way communication. You can obtain credit card or investment opportunities from the bank. the relationship between the customer and the company is becoming weaker over time. You don’t need to contact the car dealer or manufacturer once a week or a month. and behavioral data. Software was organized by account number. club shops. Since 1993. However. your relationship or dependence to the bank increases. transfer money. with each backend system using its own numbering system. For example. Wells Fargo is one of the leading banks which transforms these relationships into opportunities. pay bills.

By using online banking. It built a Web site as a new contact point in 1995 and provided advanced technologies to its customer. In the future. customers can manage their account anytime and anywhere. These changes increase convenience for both customers and service agents.of the account numbers. By providing more power to manage their account and money. Wells Fargo expects to increase customer loyalty and obtain long term mutual benefits with its customers. 24 . Wells Fargo will try to build online customer communities (similar to America Online or the World Wide Web) in its banking service by responding to customers’ needs with new technologies. Wells Fargo provides Internet banking. Online banking also saves operating cost of the bank branches.

although this field. while statistics is human driven. data mining is data driven. rules. That is. 25 . Results of the data mining process may be insights. like most of the rest of statistics. data mining attempts to extract knowledge from data. Data mining differs from traditional statistics in several ways: formal statistical inference is assumption driven in the sense that a hypothesis is formed and validated against the data. in this sense data mining is human centered and is sometimes coupled with human-computer interfaces research. Said another way. anomalies. Data mining in contrast is discovery driven in the sense that patterns and hypothesis are automatically extracted from data. The branch of statistics that data mining resembles most is exploratory data analysis. rules. Data mining also differs from traditional statistics in that sometimes the goal is to extract qualitative models which can easily be translated into logical rules or visual representations. or predictive models. which is an interactive. has been focused on data sets far smaller than most that are the target of data mining researchers. Data mining is a step in the data mining process. changes.1 WHAT IS DATA MINING? Data mining is the semi-automatic discovery of patterns. and statistically significant structures and events in data. CHAPTER 3 DATA MINING 3. semi- automated process which begins with raw data. associations.

data mining is a natural outgrowth of a business investment in data warehousing. companies can use these findings for more profitable.1. an emerging technology based on a new generation of software. As a sophisticated decision support tool. databases. SAS Institute defines data mining as the process of selecting. and neural networks to explore large amounts of data and discover relationships and patterns that shed light on business problems. machine learning. easily accessible repository of information to support dynamic business intelligence applications. The data warehouse provides a stable.1 Overview of Data Mining To convert the value of the data warehouse or data mart into strategic business information. and modelling large amounts of data to uncover previously unknown patterns for a business advantage. 3. including statistics. By taking this "bottom up" approach to data mining and involving upper management in the understanding of business problems and the potential ROI. This process can be more efficient if you first define what the business problem is. many companies are turning to data mining. 26 . exploring. The field of data mining draws upon several roots. Data mining was designed for exploiting massive amounts of data. proactive decision making and competitive advantage. visualization. In turn. Data mining combines techniques including statistical analysis. and then determine the amount of data you will need to solve the problem. induction. the process will be much more acceptable and the goals attainable. and high performance computing.

standardized whole. Hardware advances--reduced storage costs and increased processor speed--paved the way for data mining's large-scale. the data mining process requires considerable additional effort to pre-process data.1. To exploit these vast stores of data in the data warehouse. mine the data. Companies can take data from the Internet.2 Semma 27 . neural networks. consolidated into records at the customer level. data mining became feasible in business only after new hardware and software technology advances became available. intensive analyses. companies could successfully analyze their massive databases as a coherent. organizations employ data mining to explore and model relationships in the large amounts of data in the data warehouse. Finally. Inexpensive storage also encouraged businesses to collect data at a high level of detail. and decision trees--were developed. and distribute the findings and models throughout the company via an Intranet. Software advances continued data mining's evolution. new exploratory and modeling tools--including data visualization. Without the pool of validated and "scrubbed" data that a data warehouse provides. data mining incorporated these tools into a systematic. With the advent of the data warehouse. 1: Data pyramid As the next step. the Internet can also serve as a data source. iterative process.Figure 3. 3. Although data mining tools have been around for many years. Although the data warehouse is an ideal source of data for data mining activities.

If a niche is so tiny that it's not represented in a sample and yet so important that it influences the big picture. And--like data warehousing--data mining requires a systematic approach. or as one or two specific analytic tools. correspondence analysis. which applies a reliable. and clustering. select and transform the most significant predictive variables. Beginning with a statistically representative sample of the data. Data mining is often seen as an unstructured collection of methods. model the variables to predict outcomes. Step 2: Explore Search speculatively for unanticipated trends and anomalies so as to gain understanding and ideas. data mining is not a single technique. 28 . After sampling your data. For optimal cost and performance. it can be discovered using summary methods. you can apply exploratory statistical and visualization techniques. Step 1: Sample Extract a portion of a large data set big enough to contain the significant information yet small enough to manipulate quickly. the next step is to explore them visually or numerically for inherent trends or groupings. clustering might reveal groups of customers with distinct ordering patterns. For example. explore. SAS Institute has mapped out an overall plan for data mining. However. such as neural networks. If general patterns appear in the data as a whole. and assess. Mining a representative sample instead of the whole volume drastically reduces the processing time required to get crucial business information. statistically representative sample of the full detail data. SAS Institute advocates a sampling strategy. and affirm the model's accuracy. model. in data mining for a direct mail campaign. If visual exploration doesn't reveal clear trends. This step-by-step process is referred to by the acronym SEMMA: sample. these will be traceable in a representative sample. you can explore the data through statistical techniques including factor analysis. Exploration helps refine the discovery process. but an iterative process in which many methods and techniques may be appropriate. modify. To clarify the data mining process. Knowing these patterns creates opportunities for personalized mailings or promotions.

you may need to manipulate your data to include information such as the grouping of customers and significant subgroups. you can test the model against known data. it should work for this validation sample as well as for the training data used to construct the model. The Future 29 .Step 3: Modify Create. Similarly. Based on your discoveries in the exploration phase. Step 5: Assess Evaluate the usefulness and reliability of findings from the data mining process. Because data mining is a dynamic. and is appropriate within specific data mining situations depending on the data. to narrow them down to the most significant ones. tree- based models. In addition. and transform the variables to focus the model construction process. A common means of assessing a model is to apply it to a portion of data set aside during the sampling stage sometimes known as validation data. For example. such as partial mailings in a direct mail campaign. iterative process. if you know which customers in a file had high retention rates and your model predicts retention. Modeling techniques in data mining include neural networks. logistic models. select. you can update data mining methods or models when new information is available. you are ready to construct models that explain patterns in the data. You may also need to modify data when the "mined" data change. For example. neural networks are good at combining information from predictors which support nonlinear associations with a target. you can check to see whether the model selects these customers accurately. practical applications of the model. Step 4: Model Search automatically for a variable combination that reliably predicts a desired outcome. Once you prepare your data. or to introduce new variables. help prove its validity. and other statistical models--such as time series analysis and survival analysis. For a model to be considered successful and useful. Each type of model has particular strengths. The final step in data mining is to assess the model to estimate how well it performs. You may also need to look for outliers and reduce the number of variables.

However. 3. Data mining functionality will be packaged to integrate seamlessly with existing data warehouse and business intelligence software--with the accent on solving business problems rather than on the enabling technology.3 Business Intelligence Using Data Mining Companies typically begin their business intelligence (BI) journey with a focus on understanding and measuring the outcome of past decisions. They’re evolving their BI capabilities by adding data mining technology to their operations because they know that if they don’t — they’ll perish at the hands of competitors that do. In learning more about themselves and their customers. data mining is a technology that is quickly gaining momentum in the market place.1. But these “rear-view mirror” technologies can’t provide you with a clear picture of the future — they only give you a view of the road behind you. The Gartner Group estimates that over the next 10 years the use of data mining in target marketing applications will increase from less than 5% to more than 80%. The most evolved business intelligence continually applies data mining techniques and deploys the results enterprise-wide. these organizations will see a shift towards true one-to-one relationships with the customers-- ensuring complete customer relationship management. By all accounts. 30 . Data mining looks forward to tell you what is most likely to happen — giving you the power to improve your future. As a result. Accurate anticipation of the customers' actions can lead to increased effectiveness of marketing activities and decreased financial risks. organizations using data mining techniques will be able to understand key business issues more thoroughly and to present the results of analysis meaningfully to specialist marketing analysts and general users alike. The META Group estimates that the data mining market will grow to $300 million by 1997 and to $800 million by the year 2000. Industry leaders are realizing that forward looking business intelligence is imperative to making better decisions that solve business problems and keep their companies moving in a profitable direction. the real promise of data mining is that software products will increasingly be focused on business solutions.

3.2 PRIVACY Privacy is an important issue that must be addressed in most Data Mining exercises. Laws in many countries directly affect Data Mining and are required knowledge—penalties are often severe. They began with reporting that gave them simple measurements.1 OECD Principles of Data Collection o Collection limitation: Data should be obtained lawfully and fairly. Focused their BI on the future with data mining. Added OLAP to drill-down to more detail. 3. And finally deployed data mining results to their front lines to continually improve ROI. 2 This graph shows how a wireless telco has evolved their BI — an evolution to solving the problems that affect future profits.2. while certain very sensitive data should not be held at all 31 .Figure 3. There are OECD Principles of Data Collection.

or misuse of data o Openness: It must be possible to acquire information about the collection. proper precautions should be taken to ensure this accuracy o Purpose specification: The purposes for which data will be used should be identified. storage. destruction. corruption. complete and up-to-date. and the data should be destroyed if it no longer serves the given purpose o Use limitation: Use of data for purposes other than specified is forbidden. and use of personal data o Individual participation: The data subject has a right to access and challenge the data related to him or her o Accountability: A data controller should be accountable for complying with measures giving effect to all these principles 32 . accurate. except with the consent of the data subject or by authority of law o Security safeguards: Agencies should establish procedures to guard against loss.o Data quality: Data should be relevant to the stated purposes.

2 STEP 2: Finding Statistical Values Of The Calling Times 33 . we analyzed some simulated calling data. Our work will be presented below into steps. their needs and it is possible to classify the customers. It was impossible to evaluate all these tariffs so we determined the most affective ones which are used totally more than %90 of customers.2 STEPS OF OUR WORK 4.2.2. 4.1 INTRODUCTION Aim of this project is to establish a Customer Relationship Management System to a GSM operator. 4. In order to achieve this target. There were more than 50 tariffs in our simulated data. whose calling behaviors are similar. CHAPTER 4 CASE STUDY 4. Data analyzing and data mining are very important part of CRM because by this way it is possible to determine customer behaviors.1 STEP 1: Determining The Most Used Tariffs And The Cities That The Operator Is Used Most We used Pareto analysis to determine the most used and the most affective tariffs from the simulated data. into clusters.

2. 1: one variable analysis window Statgraphic Statgraphic is used as a statistic software and all the data are sent partially to the Statgraphic in order to find statistical values. Figure 4.1 Analysis Summary 34 .2. Menus that are used in our project will be shown below: 4.1.1 Describe => Numeric Data => One Variable Analysis From this analysis.1. We obtain statistical values of our data from these tables. we used analysis summary and summary statistics tables.

2: a sample of Analysis Summary window 4.figure Summary Statistics figure 4.1. 3: a sample of summary statistic window Describe => Distributions => Distribution Fitting(Uncensored Data) 35 . Analysis Summary figure 4.2. 4: a sample of Analysis summary window 4.4.3 STEP 3: Preparing Reports of These Data 36 .

5: a sample of Density trace diagram figure 4. density trace and scatter plots. We supported our reports with histograms. 6: a sample of Histogram diagram 37 . These plots are obtained from one variable analysis and distribution fitting menus. See Appendix A Pareto analysis of tariffs for 3 months See Appendix B for report of detailed analysis of each tariff ( for month_x) See Appendix C for reports of 3 months (statistical values and graphics) See Appendix D for report of 3 big cities’ most used tariffs See Appendix E for reports of the most used tariffs of month_x figure 4.

customers’ calls inside GSM company’s network is about 15-25 minutes per each person. it is seen that this value is very low.4.1 General Evaluation of Tariffs o Except Tariff 3. by this way to increase their profit margin and number of customers. We recommend that some changes in the application of tariffs should be applied.2. GSM operator may apply a cheaper tariff to SMS such as decreasing the contour per message. 38 . o SMS usage is 1 message per day per customer which is very small value.2. This shows that customers are in contact with people which use other GSM operators so the existing customers of GSM company may have a tendency to skip to other GSM operators which will make their inside-network calls cheaper. o This GSM operator’s customers make fixed-line calls as the same rate of inside-network calls. o When we observe the tariffs.4 STEP 4: Evaluate These Reports 4. we see that outside- network calls are moderately more than inside network calls. 7: a sample of scatter plot 4. Generally GSM companies’ primary aim is to increase inside-network calls. This shows us that GSM operator applies a suitable or maybe cheaper tariff to customers in calling to home phones. When it is compared with fixed-line and outside-network calls.figure 4.

but the inside-network and outside-network calls are lower compared with other tariffs. Similarly. o GSM company is more succesful in month_y than month_x. So we can say that this tariff is succesful in every category of calling behaviours. Also outside-network calls are nearly 2 times more than the other 6 tariffs. it is seen that special-to-tariff is used most when it is compared with the other tariffs. we can judge that this customer type is using the GSM operator just for special-to-tariff calls. fixed-line. o Tariff 3 is different from the other tariffs that we examined.2 Evaluation of Each Tariff Privately o It is observed that fixed-line calls are higher in Tariff 1.2. o Special-to-tariff calls are very succesful because it is seen that special-to-tariff calls are nearly 10 times more used than inside-network. 39 . According to the assumption that special-to-tariff is in calling to some determined numbers freely. So we can assume that in this tariff there may be a price discount in fixed- line calls. But the inside-network.4. In tariff 3. According to these data. which is not desired for the GSM operator. it can be said that company’s promotion and some applications which will attract customers calling behaviours are succesful in month_y. There is an increasing trend on every category of calling in month_y. there is no special to tariff calls so the rate of inside-network calls are very high. 4. outside-network calls are not used much. o Tariff 2 is the most used second tariff in all three months and in this tariff. Especially special-to-tariff calls are increased dramatically. outside-network or fixed-line. Fixed-line calls and the average number of SMS are much more than the other 6 tariffs.

These kind of tariffs is affective to increase the number of customers of GSM operator.2. tariff 7 doesn’t attract attention because they are average not so low not so high values are seen in these tariffs. Tariff 3 is more succesful than the other tariffs. calling the selected numbers are cheaper. Also we can say that customers of this tariff are active users of GSM operator which means that these users are using this GSM operator during whole day. 4.5 STEP 5: Tariff Recommendations For The GSM Operator o Tariff A. Even Special-to-tariff calls are limited to less than 4 hours which is very low compared with other tariff’s special-to-tariff calls. This kind of tariffs may attract customers and may increase the rate of GSM 40 . o All calling times of Tariff 6 and number of SMS are lower than the other tariffs. So it can be assumed that there is no special price applied in these calls.  Price of SMS is cheaper than normal price which is applied in many tariffs  The average number of SMS used is an indicator of target customers are youngsters which are very fond of sending messages  Outside-network calls may also be cheaper than normal price  Fixed-line calls are the same level with the other tariffs. inside network calls are cheaper. This tariff is used by many GSM operators in Turkey. o We estimate that cheaper calling prices or maybe free calling in inside-network is appliable in Tariff 3.The clues that support our thesis are the average calling times of outside-network (nearly 2 times more than other tariffs) and average number of messages(nearly 2 times more than other tariffs). Tariff 3 is able to make the customers to use the GSM operator actively. o Tariff 4. o Tariff B. o Our assumptions on Tariff 3 which may make this tariff succesful. tariff 5. There is no special-to-tariff application in this tariff.

o Tariff D. GSM operator may offers special tariffs to different customer segments such as. 41 . This tariff has the same mentality with Tariff E. calls more than 7 minutes are 200.. o Tariff G. special tariffs to some customer segments.. time restricted tariff. nights (between 23. Cheaper pricing is used in some slice of time such as. generally hours. 100 minute package or 200 minute package. which are not prefered by the customers to make calls. GSM operator may offer less price in calling to the people with the same profession. So it can be said that this kind of tariffs are usefull to garanty some amount of revenue o Tariff F.00 to 08. However if you don’t use all of these 70 messages. university students.000TL/minute. o Tariff E.000 TL/minute. call duration between 3 and 7 minutes are 300. pre-paid short message packages. policemen. In this tariff. Customer pays less than the normal price for that much calling times but if he/she don’t use that much time the payment will not dicrease. o Tariff C. the more you talk. you pay just 4 million.usage. pre-paid calling-time-packages. In this tariff messages are charged less however it increases the revenue. The aim of this tariff is to make users call in that not used times with attractive pricing.00). GSM operator gives customers the chance of selecting limited number of numbers(2 or 3). calls less than 3 minutes are 400. For example. This may reduce the calling traffic of network. the payment will not change. there is a package which is called “70 message package”. If the normal price of 70 messages are 7 million. Such as. the lower you pay. The price of calling is relevant with the time duration of your call such as. students. teachers . Customer pay less for calling if he/she chooses prepaid packages. and charges callings less.000 TL/minute.etc. According to the assumption of these customers will be generally in contact with people who are in the same profession. are prefered for these tariffs’ cheaper pricing. This kind of tariffs’s aim is to increase the calling duration so that increase profit. Operator gives customers the chance of paying less to number of messages if the customers prefer to pay a fixed price for those messages.

42 .

The IT department needs extensive infrastructure and resources to implement CRM databases successfully. because the customer is more knowledgeable.1 Identification Of Problems o Calling times are very insufficient o SMS usage is very low(less than global montly SMS/user which is 36) 42 . and more creative than a few years ago. CRM is very hard to implement throughout a company. companies must be faster.2. Executives must be willing to support the CRM implementation process forever because CRM never ends. quicker turn-around on customer problems. and questions.1 A GENERAL LOOK TO CRM The present is an era of company loyalty to the customer in order to obtain customer loyalty to the company.2 RESULTS OF CASE STUDY 5. concerns. more agile. The Internet allows information to be obtained almost instantaneously. Consumers are more knowledgeable than ever before and. 5. and quicker feedback about customer suggestions. purchase referrals. The Internet permits firms to establish a personalized customer experience through online help. CHAPTER 5 CONCLUSION 5.

advertisements and succesful tariffs. It is imposible to promote all these tariffs to potential customers. o Standardization is necessary. o GSM operator may apply a cheaper tariff to SMS such as decreasing the contour per message. 5. o Tariffs should be promoted to top customers o GSM operator should gain customer loyalty and reliability.2. o Inside-network calls are very low in some tariffs lower than outside-network calls which shows that the users of GSM operator has a tendency to skip to other GSM operators which will make their inside-network calls cheaper. o Too many tariffs exist in the current condition. most used and succesful tariffs should be determined and GSM operator should go through these tariffs.2 Proposals To These Problems GSM company should try to increase the number of customers by promotions. if the GSM operator have a good image on people. customer will probably choose the most reliable one. than it is posiible to charge more than the other GSM operators in the market. It will be advantage in the condition which the tariffs and opportunities are very similar with other GSM operators. o Pre-paid SMS packages will increase the number of usage of SMS o Pre-paid calling times packages will increase average calling times 43 . Besides.

An Introduction to Data Mining . G. R.R . California. 2002 o Brown. 2001 o CFO research service. Solving business problems with Statistics and Data Mining. http://www.CSIRO Australia. CFO publishing corporation. and Brocklebank.upenn. SBSS Inc. Customer Relationship Management.html o SBSS BI.cis. Rocke. Mining the Value in CRM Data. 2001 o Williams. 1998 44 . Moore. M. Kasif. Data Mining. S.REFERENCES o Gray. J. 1999 o J.and Ullman.U. Data Mining Research: Opportunities and Challenges. P. D. and Byun.