Journal of Intelligence and Information Systems (지능정보연구)

Korea Intelligent Information System Society (한국지능정보시스템학회)
권호 표지

인위적 데이터를 이용한 군집분석 프로그램간의 비교에 대한 연구

  • 김성호 (한양대학교 경영대학 경영학부) ;
  • 백승익 (한양대학교 경영대학 경영학부)
  • Published : 2001.12.01
Download PDF
⟨ Previous Next ⟩

Abstract

Over the years, cluster analysis has become a popular tool for marketing and segmentation researchers. There are various methods for cluster analysis. Among them, K-means partitioning cluster analysis is the most popular segmentation method. However, because the cluster analysis is very sensitive to the initial configurations of the data set at hand, it becomes an important issue to select an appropriate starting configuration that is comparable with the clustering of the whole data so as to improve the reliability of the clustering results. Many programs for K-mean cluster analysis employ various methods to choose the initial seeds and compute the centroids of clusters. In this paper, we suggest a methodology to evaluate various clustering programs. Furthermore, to explore the usability of the methodology, we evaluate four clustering programs by using the methodology.

인터넷 비즈니스나 전자상거래와 연관되어 고객관계관리(Customer Relationship management :CRM)에 대한 관심이 널리 확산됨으로 해서 군집분석에 대한 관심이 한층 높아졌고, 다양한 군집분석 프로그램이 시장에 소개되어 지고 있다. 그런, 군집분석 프로그램들은 다른 데이터 분석 기법과는 달리 그들의 성능을 측정하기가 매우 힘들다. 본 논문에서는 이미 알려져 있는 군집구조를 지닌 인위적 데이터를 사용하여 다양한 군집분석 프로그램을 평가할 수 있는 하나의 방법론을 제시하고, 그 방법론의 유용성을 보여 주기 위해 현재 많이 사용하고 있는 네 가지의 군집분석 프로그램을 본 논문에서 제시한 방법론을 사용하여 평가하는데 그 주요 목적을 두고 있다. 본 연구에서 두 가지의 반복적 군집분석 프로그램(Convergent Cluster Analysis:CCA, SPSS의 Clementine), 전통적인 단순군집 프로그램(One-Shot Clustering Program: Howard-Harris 프로그램), 그리고 IBM의 데이터 마이닝 기법 중 하나인 데모그래픽 군집분석 프로그램의 성능을 비교한 결과, 군집분석을 위하여 다른 군집분석 방법 보다 좀 더 지능적으로 초기치를 생성한 CCA방법이 가장 우월한 성능을 보여 주었다.

Keywords

References

  1. Applied Psychological Measurement v.2 Computer Programs for Performing Iterative Partitioning Cluster Analysis Aldenderfer,M.S.;Blashfield,R.K.
  2. Cluster analysis for researchers Anderberg,M.R
  3. Journal of Marketing Research v.18 Overlapping Clustering : A New Methodolgy for Product Positioning Arabie,P.Carroll,J.DeSarbo,W.S.;Wind,Y
  4. Data Mining Techniques,Wiley Computer Publishing Berry,M.;Linoff,G.
  5. McGraw-Hill Building Data Mining Applications for CRM, Berson,A.Smith,S.;Thearling,K.
  6. Psy-Chological Bulletin v.83 Mixture Model Tests of Cluster Analysis : Accuracy of Four Agglomerative Hierarchical Methods Blashfield,R.K
  7. Psychometrika v.48 INDCLUS :An Individual Differences Generation of the ADCLUS Model and the MAPCLUS Algorithm Carroll,J.;Arabie,P
  8. Journal of Classification v.11 An Alternating Combinatorial Optimization Approach to FItting the INDCLUS and Generalized INDCLUS Models Chaturvedi,A.;Carroll,J
  9. Journal of Marketing Research v.34 A Feature-Based Approach to Market Segmentation via Overlapping K-Centroids Clustering Chaturvedi,A.Carroll,J.,Green,P.;Rotondo J
  10. Psychometrika v.47 GENNCLUS : New Models for General Nonhierarchical Clustering Analysis DeSarbo,W
  11. Journal of Market Research v.5 Numerical Taxonomy in Marketing Analysis : A Review Article Frank,R.E.;Green,P.E.
  12. Management Science v.13 Cluster Analysis in Test Market Selection Green,P.E.,Frank,R.E.,;Robinson,P.J.
  13. Journal of Marketing v.55 Segmenting Markets with Conjoint Analysis Green,P.E.;Krieger,A
  14. Multivariate Data Analysis with Readings 3rd Ed,.Macmillan Publishing Company,NY.NY Hair,J.Anderson,R.,Tatham,R.;Black,.W.
  15. Decision Science v.22 A Computational Study of Replicated Clustering with an Application to Market Segmentation Helsen,K.;Green,P.E
  16. Journal of Classification, v.2 Comparing Patitions Hubert,L.;Arabie,P
  17. ACM Computing Surveys v.31 no.3 Data Clustering A Review Jain,A.K.,Murty,M.N.;Flynn,P.J
  18. Applied Statistics v.15 Classifying Market Survey Respondents Joycce,T.;Channon,C.
  19. Mixture Models : Inferences and Applications to Clustering,New York Marcel Dekker McLachlan,G.J.;Basford,K.E
  20. Educational and Psychological Measurement v.40 A Two Stage Clustering Algorithm with Robust Recovery Characteristics Milligan,G.W.;Sokol L.M
  21. Psychometrica v.50 An Algorithm for Generating Artificial Test Clusters Milligan,G.W.
  22. Multivariate Behavioral Research v.21 A Study of Comparability of External Criteria for Hierarchical Cluster Analysis Milligan,G.W;Cooper,M.C
  23. Procedures and Pitfalls in Cluster Analysis,Proceedings,Fall Conference Chicago American Marketing Association Neidell,L.A
  24. CCA System for Convergent Cluster Analysis ,Ketchum,ID : Sawtooth software Sawtooth Software
  25. ACA System for Adaptive Conjoint Analysis,Ketchum,ID : Sawtooth Software Sawtooth Software
  26. Journal of the Market Research Society v.40 no.2 Cluster-Based Market Segmentation Some Further Comparisons of Alternative Approaches Schaffer,C.;Green,P.
  27. PC-MDS : Multidimensional Statistics Package, Institute of Business Management,Brigham Young University Smith,S.M
  28. Journal of Marketing Research v.48 A Customer-Oriented Approach for Determining Market Structures Srivastava,R.K.Alpert,ML.;Shocker,A.P.
  29. Journal of the American Statistical Association v.58 Hierarchical Grouping to Optimize an Objective Function Ward,J.H
  30. Multivariate Behavioral Research v.5 Pattem Clustering by Multivariate Mixture Analysis Wolfe,J.H.