Data Mining Techniques in Monitoring Customers’ Sector

Data Mining Techniques in Monitoring Customers’ Sector

Получение информации о секторе клиентов является для предприятия важным фактором повышения конкурентоспособности. Эффективными средствами при обработке и использовании информации в процессе принятия решений являются методики получения данных. Описаны широкие возможности технологии Data Mining Techni...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Datum:2007
1. Verfasser: Jelonek, D.
Format: Artikel
Sprache:English
Veröffentlicht: Інститут проблем моделювання в енергетиці ім. Г.Є. Пухова НАН України 2007
Schriftenreihe:Электронное моделирование
Online Zugang:https://nasplib.isofts.kiev.ua/handle/123456789/101788
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
Назва журналу:Digital Library of Periodicals of National Academy of Sciences of Ukraine
Zitieren:Data Mining Techniques in Monitoring Customers’ Sector / D. Jelonek // Электронное моделирование. — 2007. — Т. 29, № 4. — С. 83-90. — Бібліогр.: 11 назв. — англ.

Institution

Digital Library of Periodicals of National Academy of Sciences of Ukraine
id nasplib_isofts_kiev_ua-123456789-101788
record_format dspace
spelling nasplib_isofts_kiev_ua-123456789-1017882025-02-09T21:31:17Z Data Mining Techniques in Monitoring Customers’ Sector Системы управления информацией в мониторинге покупательского процесс Jelonek, D. Получение информации о секторе клиентов является для предприятия важным фактором повышения конкурентоспособности. Эффективными средствами при обработке и использовании информации в процессе принятия решений являются методики получения данных. Описаны широкие возможности технологии Data Mining Techniques на основе информационных ресурсов системы Client relation management. Отримання інформації про сектор клієнтів для підприємства є важливим фактором під вищення конкурентоспроможності. Ефективними засобами при обробці і використанні інформації у процесі прийняття рішень є методики отримання даних. Описано широкі можливості технології Data Mining Techniques на основі інформаційних ресурсів системи Client relation management. An area where enterprises are increasingly looking for the opportunity to gain competitive prevalence is that of acquiring knowledge about enterprise’s environment, particularly on the customer’s sector. An effective tool in processing and using the knowledge in decision processes is Data Mining Techniques. Wide possibilities of Data Mining Technique based on information resources of Client relation management system are described. 2007 Article Data Mining Techniques in Monitoring Customers’ Sector / D. Jelonek // Электронное моделирование. — 2007. — Т. 29, № 4. — С. 83-90. — Бібліогр.: 11 назв. — англ. 0204-3572 https://nasplib.isofts.kiev.ua/handle/123456789/101788 en Электронное моделирование application/pdf Інститут проблем моделювання в енергетиці ім. Г.Є. Пухова НАН України
institution Digital Library of Periodicals of National Academy of Sciences of Ukraine
collection DSpace DC
language English
description Получение информации о секторе клиентов является для предприятия важным фактором повышения конкурентоспособности. Эффективными средствами при обработке и использовании информации в процессе принятия решений являются методики получения данных. Описаны широкие возможности технологии Data Mining Techniques на основе информационных ресурсов системы Client relation management.
format Article
author Jelonek, D.
spellingShingle Jelonek, D.
Data Mining Techniques in Monitoring Customers’ Sector
Электронное моделирование
author_facet Jelonek, D.
author_sort Jelonek, D.
title Data Mining Techniques in Monitoring Customers’ Sector
title_short Data Mining Techniques in Monitoring Customers’ Sector
title_full Data Mining Techniques in Monitoring Customers’ Sector
title_fullStr Data Mining Techniques in Monitoring Customers’ Sector
title_full_unstemmed Data Mining Techniques in Monitoring Customers’ Sector
title_sort data mining techniques in monitoring customers’ sector
publisher Інститут проблем моделювання в енергетиці ім. Г.Є. Пухова НАН України
publishDate 2007
url https://nasplib.isofts.kiev.ua/handle/123456789/101788
citation_txt Data Mining Techniques in Monitoring Customers’ Sector / D. Jelonek // Электронное моделирование. — 2007. — Т. 29, № 4. — С. 83-90. — Бібліогр.: 11 назв. — англ.
series Электронное моделирование
work_keys_str_mv AT jelonekd dataminingtechniquesinmonitoringcustomerssector
AT jelonekd sistemyupravleniâinformacieivmonitoringepokupatelʹskogoprocess
first_indexed 2025-12-01T00:19:52Z
last_indexed 2025-12-01T00:19:52Z
_version_ 1850263097050136576
fulltext D. Jelonek, PhD Management Department, Czestochowa Technical University (Al. Armii Krajowej 19b, 42-200 Czestochowa, Poland, E-mail: jelonek@zim.pcz.czest.pl) Data Mining Techniques in Monitoring Customers’ Sector An area where enterprises are increasingly looking for the opportunity to gain competitive preva- lence is that of acquiring knowledge about enterprise’s environment, particularly on the cus- tomer’s sector. An effective tool in processing and using the knowledge in decision processes is Data Mining Techniques. Wide possibilities of Data Mining Technique based on information re- sources of Client relation management system are described. Ïîëó÷åíèå èíôîðìàöèè î ñåêòîðå êëèåíòîâ ÿâëÿåòñÿ äëÿ ïðåäïðèÿòèÿ âàæíûì ôàêòîðîì ïîâûøåíèÿ êîíêóðåíòîñïîñîáíîñòè. Ýôôåêòèâíûìè ñðåäñòâàìè ïðè îáðàáîòêå è èñïîëü- çîâàíèè èíôîðìàöèè â ïðîöåññå ïðèíÿòèÿ ðåøåíèé ÿâëÿþòñÿ ìåòîäèêè ïîëó÷åíèÿ äàí- íûõ. Îïèñàíû øèðîêèå âîçìîæíîñòè òåõíîëîãèè Data Mining Techniques íà îñíîâå èíôîðìàöèîííûõ ðåñóðñîâ ñèñòåìû Client relation management. K e y w o r d s: data mining, customer’s sector, CRM, monitoring. Scanning environment process. Today’s turbulent business environment char- acterised by uncertainty and inability to predict the future is extremely challeng- ing, and thus requires the development of new competences. Companies that are willing to survive in competition must react to the changes quickly. These changes are numerous and challenges to re-engineer or adapt with continuous improvement are numerous, too. Business environment is the division to macroenvironment and competitive environment [1]. This division makes easier performing observations, research and environment analysis. Macroenvironment includes following segments: economic, political, social, technological, demographic, legislative and interna- tional. Competitive environments consist of all economic entities that have co- operative or competitive connections with the company. The distinction be- tween macroenvironment and competitive environment has generally method- ological nature and require taking into account its specific elements. In competitive environment, opposing to macroenvironment the effects of environment influence on the business are more remarkable and can became no- ticeable in significantly shorter time. From the macroenvironment point of view ISSN 0204–3572. Ýëåêòðîí. ìîäåëèðîâàíèå. 2007. Ò. 29. ¹ 4 83 some changes can be of low importance but from the point of view of objects that the changes apply to the information are of great importance. Therefore the enterprises should ensure their access to accurate, high quality information about the environment, use modern and efficient analytical tools that allow fast and synthetic diagnose its functioning and determining its position in compari- son with competitors. A verified research method in this area is environment scanning. Scanning provides constant control over particular environment indexes according to as- sumed premises. It also allows taking full advantage of tools supplying informa- tion about appearing differences from the assumptions. Environmental scanning is aimed at creating a reasonable appreciation and vision of the context for business operation, and to alert managers to the possible shift or invalidation of old appreciation. Scanning is both purposeful search and undirected viewing. A complete scanning process is an interactive process of search and noting (data collection), meaning developing and impact analysis (in- terpretation), as ell as learning (adaptive action taken) [2]. Enterprise’s environment monitoring with the use of Client relation management (CRM) system. Numerous interpretations of CRM can be found in relevant literature. The CRM is understood as a method of managing the most important clients, as an information system or as a business philosophy. The ba- sic assumption underlying the CRM philosophy is the individual handling of each client and maintaining constant contact with him. Scott defines CRM as a set of business processes and overall policies de- signed to capture, retain and provide service to customers [3]. Shahnam defines CRM as the first and foremost business strategy for realiz- ing higher profit and enhanced competitive advantage, which comprises three fundamental aspects: operational CRM, analytical CRM and collaborative CRM [4]. It was mentioned that CRM application architecture must combine opera- tional and analytical and collaborative technologies [5, Fig. 1]. Operation systems, such as the ERP, SCM systems, are responsible for the everyday maintenance of business processes. These systems are independent of each other and constitute a basic source of data for the remaining parts of the ar- chitecture. The most important element in the analytical module is the Data Mart, or an integrated, time-invariable store of thematic data, encased in special analytical systems that enable the retrieving of knowledge from the stored data and discov- ering new relationships using the Data Mining Techniques. Data Marts store common information aggregates that are subsequently used for multi-dimen- sional analyses. The interactive CRM (the communication layer) allows direct contact with a client, offering both traditional and modern communication channels. The CRM D. Jelonek 84 ISSN 0204–3572. Electronic Modeling. 2007. V. 29. ¹ 4 is a system assisting in cooperation with the customer and in information ex- change among the enterprise’s departments. CRM systems basically make three things possible: having an integrated, single view of customers, by using analytical tools; managing customer relationships in a single way, regardless of the commu- nication channel: telephone, website, personal visit, and so forth; improving the effectiveness and efficiency of the processes involved in cus- tomer relationships. As a result, the implementation of a CRM system will involve changes in the organisation and operation of each company, resulting in an improvement in its performance and competitiveness. The most notable improvements that can be predicted are the following [6]: greater customer satisfaction, through offering a better service; greater business coherence, defining corporate objectives linked to cus- tomer satisfaction; managing to increase the number of customers and secure greater loyalty thanks to the reorganisation and computerisation of business processes sur- rounding the customer relations life-cycle (sales, marketing, customer care services); improving and extending customer relationships, generating new business opportunities; Data Mining Techniques in Monitoring Customers’ Sector ISSN 0204–3572. Ýëåêòðîí. ìîäåëèðîâàíèå. 2007. Ò. 29. ¹ 4 85 ERP SCM Legacy system Marketing automation Service automation Sales automation Mobile sales Field service Data Werehouse Customer Activity Data Mart Customer Data Mart Product Data Mart Marketing Automation Voice (IVR, ACD) Conferencing Web Conf. E-mail Web Storefront Direct Interaction Operational CRM Analitical CRM Collaborative CRM OLAP Data Mining Back Office Front Office Mobile Office Customer interaction Fig.1. The architecture of CRM system: ERP is a Enterprise Resource Planning; SCM is a Sup- ply Chain Management; IVR is a Interactive Voice Response; ACD is a Automatic Call Distri- bution; OLAP is a On-Line Analytical Processing knowing how to segment customers, differentiating profitable customers from those who are not, and establishing appropriate business plans for each case; increasing the effectiveness of providing customer service by having com- plete, homogeneous information; lower costs; sales and marketing information about customer requirements, expectations and perceptions in real time. Achievement of above effects is possible thanks application of OLAP tools and most of all the use of Data Mining Techniques, which based onto huge data collections will be generating the knowledge of enterprise concerning monitored segment of customers. The definition and evolution of data mining. Data mining is also defined as a sophisticated data search capability that uses statistical algorithms to dis- cover patterns and correlations in data. The term is an analogy to gold or coal mining; data mining finds and extracts knowledge («data nuggets») buried in corporate data warehouses, or information that visitors have dropped on a website, most of which can lead to improvements in the understanding and use of the data. The data mining approach is complementary to other data analysis techniques such as statistics, OLAP, spreadsheets, and basic data access. In sim- ple terms, data mining is another way to find meaning in data [7]. Data mining is also defined as the process of searching and analyzing data in order to find implicit, but potentially useful, information. It involves selecting, D. Jelonek 86 ISSN 0204–3572. Electronic Modeling. 2007. V. 29. ¹ 4 Stage Business question Enabling technologies Product providers Characteristics Data col- lection 1960s What was my aver- age total revenue over the last five years? Computers, tapes, disks IBM, CDC Retrospective static data delivery Data access 1980s What were unit sales in New Eng- land last March? Relational databases (RDBMS), Structured query language (SQL), Open database connec- tivity (ODBC) Oracle, Sybase, Informix, IBM, Microsoft Retrospective dy- namic data delivery at record level Data nav- igation 1990s What were unit sa- les in New England last March? Drill down to Boston On-line analytic pro- cessing (OLAP), multi- dimensional databases, data werehouses Pilot, IRI, Arbor, Evolutionary tech- nologies Retrospective dy- namic data delivery at multiple levels Data min- ing 2000 What’s likely to happen in Boston unit sales next month? Why? Advanced algorithms, multiprocessor compu- ters, massive databases Lockheed, IBM, SGI Prospective, proac- tive information de- livery Table 1. Evolutionary stages of data mining exploring and modeling large amounts of data to uncover previously unknown patterns, and ultimately comprehensible information, from large databases [8]. Data mining techniques are the result of a long research and product devel- opment process. The origin of data mining lies with the first storage of data on computers, continues with improvements in data access, until today technology allows users to navigate through data in real time. In the evolution from business data to useful information, each step is built on the previous ones. Table 1 [7] shows the evolutionary stages from the perspective of the user. In the first stage specific application programs were created for collecting data and calculations. Data Collection, individual sites collected data used to make simple calculations. At the second step company-wide policies for data collection and reporting of management information were established. Because every business unit con- formed to specific requirements or formats, businesses could query the informa- tion system regarding branch sales during any specified time period. On-line analytic tools provided real-time feedback and information ex- change with collaborating business units (Data Mining). This capability is useful when sales representatives or customer service persons need to retrieve cus- tomer information on-line and respond to questions on a real-time basis. Data Mining Techniques in Monitoring Customers’ Sector ISSN 0204–3572. Ýëåêòðîí. ìîäåëèðîâàíèå. 2007. Ò. 29. ¹ 4 87 DEPENDENCY ANALYSIS Associations Sequences CONCEPT DESCRIPTION Summarization Discrimination Comparison CLASS IDENTIFICATION Mathematical taxonomy Concept clustering DEVIATION DETECTION Anomalies Changes DATA VISUALIZATION Piksel oriented Geometric projection Graph based DATA MINING TASKS Fig. 2. A taxonomy of data mining tasks With the application of advanced algorithms, data mining uncovers knowl- edge in a vast amount of data and points out possible relationships among the data. Data mining help businesses address questions such as, «What is likely to happen to Boston unit sales next month, and why?» Each of the four stages were revolutionary because they allowed new business questions to be answered accurately and quickly [7]. The scope of data mining methods usage. Selection of appropriate method of data analysis is dependent on character of a given problem. Data mining tasks are used to extract patterns from large data sets. The various data mining tasks can be broadly divided into five categories. Overview of chosen methods is pre- sented in Fig. 2. The taxonomy reflects the emerging role of data visualization as a separate data mining task, even as it is used to support other data mining tasks. Different data mining tasks are grouped into categories depending on the type of knowl- edge extracted by the tasks. The identification of patterns in a large data set is the first step to gaining useful marketing insights and making critical marketing decisions. Data mining in monitoring customers’ sector. Segment of customers is a very changeable area due to its range, structure, qualitative and quantitative changes. The knowledge about possible changes which may occur in a segment D. Jelonek 88 ISSN 0204–3572. Electronic Modeling. 2007. V. 29. ¹ 4 Type of analysis Purpose Customer value analysis Better understanding of own clients, improving the effectiveness of mar- keting actions, individualizing and customizing the offer Customer satisfaction analysis Development of services and products in order to enhance the satisfac- tion of customers, planning of actions aimed at enhancing the customer’s satisfaction Customer loyalty anal- ysis Undertaking effective actions aimed at retaining clients, developing loy- alty programmes Multidimensional client segmentation Better understanding of the client, the customization of the offer and the personalization of the forms of contact. Enhancing the effectiveness of marketing actions Basket analysis Effective recommendation of products to clients, better planning of of- fers, increasing sale efficiency Predictive classifica- tion and modelling Reducing the number of questions that must be posed to the client in or- der to adequately determine his most important features in the context of mutual cooperation Analysis of turning points in relationships with the client Predicting changes in customers’ behaviour, adjusting to those changes, undertaking proactively any actions that meet the customer’s expected needs Table 2. The types and purpose of analyses within the data mining is very valuable for people who are managers of a company. Data mining may provide the knowledge which is helpful in monitoring the changes of sector’s range and its structure as well. For example, outlays incurred for acquiring a new client are much higher than the costs of keeping a once won client. It is therefore worth collecting com- prehensive information of each client, recording his data, examining his behav- iour and expectations, so as to subsequently take advantage of the CRM system and its analytical capabilities in the assessment of clients. Data mining offers comprehensive analyses concerning the relationship with the customer. The types and purpose of analyses within the Data mining are given in Table 2 [9, 10]. The available analysis will enable the optimization of the links with the cus- tomer in the long run. The system identifies the company’s best customer and as- sists in activities towards the particular care of those customers. Data mining will help to make an early identification of a client who might give up the company’s services, while the loyalty actions undertaken in time may dissuade him from making such a decision. Summary. Enterprises which want to achieve competitive advantage on the market must constantly monitor its environment, especially customers’ sector. However monitoring procedures and tools in a classic view are not sufficient any more [2, 11]. Certain stages of the process such as: observation and data gather- ing are still inducted to employees of enterprise, who are in the nearest of moni- tored area (marketing department, sales department, service). Observers of a sector care of constant feeding of information resources of CRM system. Infor- mation technology also allows for other possibilities of customer’s data gather- ing and for feeding databases (email, IVR, sms…. ) Performance of analytic CRM is based onto gaining, storing, processing and interpreting data concerning customers. The most important analyses created by Data Mining are based on data coming from different sources data warehouse, and they are stored in customer’s data repository. Those data undergo complex statistical analyses thanks to which the knowledge about customers’ needs, pur- chase preferences, behaviors is obtained etc. Provided knowledge enable to cor- rectly interpret signals from environment e.g. predict changes in purchase pref- erences of customers. Among many advantages resulting from Data Mining application in cus- tomers’ sector monitoring it is worth to score under the possibility of customers’ knowledge distribution, estimation of customer’s value in time, survival time analysis or analysis of customer’s departure to the competitiveness company. Data Mining Techniques in Monitoring Customers’ Sector ISSN 0204–3572. Ýëåêòðîí. ìîäåëèðîâàíèå. 2007. Ò. 29. ¹ 4 89 Îòðèìàííÿ ³íôîðìàö³¿ ïðî ñåêòîð ê볺íò³â äëÿ ï³äïðèºìñòâà º âàæëèâèì ôàêòîðîì ï³ä- âèùåííÿ êîíêóðåíòîñïðîìîæíîñò³. Åôåêòèâíèìè çàñîáàìè ïðè îáðîáö³ ³ âèêîðèñòàíí³ ³íôîðìàö³¿ ó ïðîöåñ³ ïðèéíÿòòÿ ð³øåíü º ìåòîäèêè îòðèìàííÿ äàíèõ. Îïèñàíî øèðîê³ ìîæëèâîñò³ òåõíîëî㳿 Data Mining Techniques íà îñíîâ³ ³íôîðìàö³éíèõ ðåñóðñ³â ñèñòåìè Client relation management. 1. Gierszewska G., Romanowska M. Analiza strategiczna przedsiêbiorstwa, wyd. II. — Warszawa : Pa�stwowe Wydawnictwo Ekonomiczne, 1998. — 310 p. 2. Aguilar F. J. Scanning the business environment. — N. Y. : MacMillan, 1967. — 3. Scott D. Understanding Organizational Evolution: Its Impact on Management and Perfor- mance. — Quorum Books, 2001. — 248 p. 4. Shahnam E. The Customer Relationship Management Ecosystem. Http//www.metagroup.com/ communities/pdfs/ad724.pdf, 2000. 5. Sohn S. Y., Lee S. J. Cost of ownership model for a CRM system, Science of Computer Pro- gramming. — 2006. — 60. — P. 68—81. 6. Bergeron B. Essentials of CRM: Customer Relationship Management for Executives. — N.Y.: John Wiley & Sons, 2001. — 220 p. 7. Rygielski Ch., Wang J-Ch., Yen D. C. Data mining techniques for customer relationship man- agement//Technology in Society. — 2002. — 24. — P. 483—502. 8. Shaw M. J., Subramaniam Ch., Tan G. W. Knowledge managenent and data miting for mar- keting//Decision Suport Systems. — 2001. — 31. — P. 127—137. 9. Banasik A., Beliczynski� J. Zarzadzanie relacjami z klientami. Aplikacje systemu CRM. — Kraków: Wydawnictwo Akademii Ekonomicznej, 2003. — P. 15. 10. Koscio w� � Sz., Pondel M., Kotwica A. Zastosowanie technologii dr��zenia danych w syste- mach klasy CRM w oparciu o �rodowisko ORACLE Owoc M.L. (red.).— Wroc�aw: Wydawnictwo Akademii Ekonomicznej im. Oskara Langego, 2003. — P. 230. 11. Choo C. W. Information management for the intelligent organizations: The art of scanning environment. — Medford, NJ : ASIS Monograph Series. Information Today, Inc., 1995. — 240 p. Ïîñòóïèëà 30.03.07 D. Jelonek 90 ISSN 0204–3572. Electronic Modeling. 2007. V. 29. ¹ 4

Ähnliche Einträge