客戶關係管理已成為現代企業卓越的商業策略之一，其中客戶保留和客戶服務被公認是最重要且具效益的商業活動。客戶關係管理目前可仰賴多樣的智慧型技術，本論文即針對客戶保留及障礙排除等客戶服務工作，提出新穎的方法來妥適整合各項智慧型技術，俾能自動淬取出有助於增裕營收之可行動知識。
在客戶保留工作方面，我們提出了一個「先分類再分群」的機制，針對可能流失客戶的特有屬性，自動找出可行動客戶保留策略來。我們先採用決策樹分類演算法來開發流失預測模型，再提出兩種不同方式來建構保留策略模型並加以應用。第一種方式使用改良過的階層式自動成長自我組織映射圖分群技術，先將流失客戶區分成為數個經明確標記的群集，再針對這些標記手動給定對應的具體保留策略。第二種方式則是運用關聯式規則探勘技術，從所有流失客戶的屬性值間找出關係，來建立出客戶流失關聯屬性值群集模型。我們特地建構了一個廣泛對應於客戶叛離的種種可能原因之客戶保留策略知識本體。藉由此知識本體之協助，即可利用客戶流失關聯屬性值群集模型來進一步建立出保留策略模型。此保留策略模型記錄了客戶群集與合適保留策略間的對應關係，因此可自動提供可行動保留策略給高值之潛在流失客戶。
在客戶服務方面，我們著重於針對真實客戶服務資料庫做知識探勘來自動建構障礙排除規則庫之方法。此障礙排除規則庫可針對客戶所提出的使用問題，提出可行動解答，除可減輕客服中心的人力負荷，復得提供客戶高品質的即時服務。為了能妥善處理真實資料庫，我們提出了一個「知識本體支援之資料修整技術」。利用文字探勘技術，我們從「備註資料欄」中擷取內含之有意義資訊，並據以修整資料庫。修整後之資料庫便可以用資料探勘模組來挖掘出更多隱含之障礙排除規則來，以提供更好之障礙排除解答給客戶。
我們以行動通信領域做為實際案例研究，並在一個真實客戶服務歷史資料庫上進行實驗。實驗證明，我們所提的方法論不僅有理論上的依據，也具備了實務上的效益。在客戶保留工作上，經由採用貪婪演算法來進行模型最佳化以及特徵選擇後，令我們驚異的，客戶社經相關屬性並非總是決定客戶是否叛離的重要因子。實驗結果也顯示，只具十個屬性的流失預測模型也能得到頗高的預測準確度。在障礙排除服務上，我們引進了限制式關聯式規則探勘技術，並且解決了在建構可行動障礙排除規則庫過程中，所遭遇的兩個主要問題，亦即，「稀有項目問題」以及「異常規則問題」。此外，在規則推論的過程中，我們均將規則本身的「信心度」明確地考慮進去，因此最後得到的結果是以一組依信心度大小而排列的可能解答。這個設計可以有效改善單一解答所可能造成的錯誤判斷。我們也很小心地在規則鏈結時利用信心度計算技巧來抑制傳遞誤差。我們的實驗亦證明了可以從修整後之資料庫，得到更多有意義的詞彙，並可進一步獲得更多有用的障礙排除規則，與直接從原始資料庫進行規則探勘相比，我們的方法確能得到更高的總體規則準確度。

Customer relationship management (CRM) has become one of the preeminent business strategies of modern business. Among the CRM efforts, customer retention and customer service are believed to be the most important and effective business activities. Nowadays, intelligent techniques are becoming more than necessary for CRM tasks. In this dissertation, we propose several novel ways for customer retention and customer service, by integrating proper intelligent techniques to help automatically extract the real nuggets of knowledge: actions useful for making profit.
In customer retention, we propose a classification-followed-by-clustering mechanism to automatically discover actionable customer retention policies for possible churners according to their specific characteristics. We use the decision tree-based algorithm to develop a churn predictive model. We then propose and compare two different approaches for constructing retention policy model and applying the models. The first approach handles the policy proposing issue by segmenting the churners into distinctly labeled clusters using modified GHSOM. With these labeled churner clusters, specific retention policies are manually associated. The second approach creates a churn attribute cluster model by exploiting the correlations among the attribute values of all churners using an association rules mining technique. With the support of retention policy ontology, which contains comprehensive retention policies corresponding to possible causes of customer defection, the churn attribute cluster model allows us to create a retention policy model that maps the clusters to appropriate retention policies. This mapping can then be used to automatically propose actionable retention policies for valuable churners.
In customer service, we focuses on automatically constructing a troubleshooting rule base by mining a real-life customer service database, and then uses the rule base to provide actionable solutions to the usage problems reported by the customers, so as to both relieve the manpower shortage of the call center and provide real-time quality service. In order to properly deal with a real-life database, we introduces an “ontology-supported refurbishing” technique by using text-mining techniques to retrieve significant information embedded in the remark fields to “refurbish” the database. The refurbished database can correctly attribute each service record with better physical meanings. The refurbished database then can be processed using a data mining module to discover implicit troubleshooting rules, which can be used to provide better troubleshooting solutions to customers.
Taking the wireless telecommunication domain as a case study, our study demonstrates both the theoretical and practical strengths of the proposed methodology via experimenting on real-life historical customer services database. In customer retention, a very interesting finding that the demographic-related attributes may not always be crucial in deciding customer defection is revealed via introducing the greedy algorithm to do model optimization and feature selection. Experimental results showed that the churn predictive model, containing only ten attributes, can reach a high degree of prediction accuracy. In troubleshooting service, we utilize a constrained association rules mining method and have solved two significant problems during the construction of actionable troubleshooting rules, namely, the “rare item problem” and the “anomalous rule problem”. The “confidence” value of a mined rule is explicitly taken into consideration in the rule inference phase, therefore the results contain a list of possible processes ranked in the descending order of the confidence values. This design can effectively alleviate potential wrong judgment with only one result. We also carefully introduce a confidence calculation mechanism for rule chaining to suppress propagating errors. From the refurbished database, our experiments demonstrated that more significant terms and more useful troubleshooting rules can be derived and the total accuracy of the set of mined rules is significantly increased than that from the original database.

[1] TM Forum, “eTOM, Enhanced Telecom Operations Map,” http://www.tmforum.org/browse.aspx?catID=1647.
[2] H. Hwang, T. Jung, and E. Suh, “An LTV Model and Customer Segmentation Based on Customer Value: A Case Study on the Wireless Telecommunication Industry,” Expert Systems with Applications, vol. 26, pp. 181-188, 2004.
[3] M. Schwaiger and H. Locarek-Junge, “Realising customer retention potentials by electronic banking,” Electron. Markets, vol. 8, no. 4, pp. 23–26, 1998.
[4] SearchCRM, “New Trends in Customer Loyalty Programs,” http://searchcrm.techtarget.com/expert/KnowledgebaseAnswer/0,289625,sid11_gci1035280,00.html.
[5] SearchCRM, “Getting Loyalty Programs Right,” http://searchcrm.techtarget.com/originalContent/0,289142,sid11_gci992695,00.html.
[6] Oceansblue, “Accurate Customer Churn Prediction with Information Inventor,” http://www.oceansblue.co.uk/resources/iichurn1. pdf.
[7] M. C. Mozer, R. Wolniewicz, and D. B. Grimes, “Predicting Subscriber Dissatisfaction and Improving Retention in the Wireless Telecommunications Industry,” IEEE Transactions on Neural Networks, vol. 11, no. 3, pp. 690-696, May 2000.
[8] Anderson Consulting, Battling Churn to Increase Shareholder Value: Wireless Challenge for the Future, Anderson Consulting Research Report (2000).
[9] A. Berson, S. Smith, and K. Thearling, Building Data Mining Applications for CRM, McGraw-Hill, 1999.
[10] Wikipedia, “Customer Relationship Management,” http://en.wikipedia.org/wiki/Customer_relationship_management.
[11] S. Sumathi and S. N. Sivanandam, Introduction to Data Mining and its Applications, Springer, 2006.
[12] M. J. A. Berry and G. Linoff, Mastering Data Mining: the Art and Science of Customer Relationship Management, John Wiley & Sons, 2000.
[13] J. Han and M. Kamber, Data Mining: Concepts and Techniques, Morgan Kaufmann Publishers, San Mateo CA, 2001.
[14] Q. Yang, J. Yin, C. Ling, and R. Pan, “Extracting Actionable Knowledge from Decision Trees,” IEEE Transactions On Knowledge And Data Engineering, vol. 19, no. 1, pp. 43-56, 2007.
[15] Z. He, X. Xu, and S. Deng, Data Mining for Actionable Knowledge: A Survey, Technical Report: arXiv:cs/0501079, 2005.
[16] Z. He, X.Xu, S. Deng, and R. Ma, “Mining Action Rules from Scratch,” Expert Systems with Applications, vol. 29, pp. 691-699, 2005.
[17] C. X. Ling, T. Chen, Q. Yang, and J. Chen, “Mining Optimal Actions for Intelligent CRM,” Proceedings of ICDM’02, pp. 767-770, 2002.
[18] J.-J. Jonker, N. Piersma, and D. V. d. Poel, “Joint Optimization of Customer Segmentation and Marketing Policy to Maximize Long-term Profitability,” Expert Systems with Applications, vol. 27, no. 2, pp. 159-168, 2004.
[19] D. T. Larose, Discovering Knowledge in Data: an Introduction to Data Mining, Wiley Interscience, 2005.
[20] P. Chapman, J. Clinton, R. Kerber, T. Khabaza, T. Reinart, C. Shearer, and R. Wirth, CRISP-DM Step-by-step Data Mining Guide, http://www.crisp-dm.org.
[21] A. Silberschatz and A. Tuzhilin, “What Makes Patterns Interesting in Knowledge Discovery Systems,” IEEE Transactions on Knowledge and Data Engineering, vol. 8, no. 6, pp. 970-974, 1996.
[22] Z. Ras and A. Wieczorkowska, “Action-Rules: How to Increase Profit of a Company,” Proceedings of PKDD’00, pp. 587-592, 2000.
[23] Z. He, X. Xu, and S. Deng, “Mining Cluster-Defining Actionable Rules,” Proceedings of NDBC’04, 2004.
[24] S. D. Bay and M. J. Pazzani, “Detecting Group Differences: Mining Contrast Sets,” Data Mining and Knowledge Discovery, vol. 5, no. 3, pp. 213-246, 2001.
[25] K. S. Ng and H. Liu, Customer Retention via Data Mining, Kluwer Academic Publishers, 1999.
[26] L. Yan, D. J. Miller, M. C. Mozer, and R. Wolniewicz, “Improving Prediction of Customer Behavior in Nonstationary Environments,” Proceedings of International Joint Conference on Neural Network, vol. 3, pp. 2258-2263, 2001.
[27] SAS Company, Predicting Churn: Analytical Strategies for Retaining Profitable Customers in the Telecommunications Industry, A SAS White Paper, 2001.
[28] W. H. Au, K. C. C. Chan, and X. Yao, “A Novel Evolutionary Data Mining Algorithm With Applications to Churn Prediction,” IEEE Transactions On Evolutionary Computation, vol. 7, no. 6, pp. 532-545, December 2003.
[29] Y. Zhang, J. Qi, H. Shu, and Y. Li, “Case Study on CRM: Detecting Likely Churners with Limited Information of Fixed-line Subscriber,” Proceedings of 2006 International Conference on Service System and Service Management, vol. 2, pp. 1495-1500, 2006.
[30] S. Berson, K. Thearling, and S. J. Smith, Building Data Mining Applications for CRM. McGraw-Hill Professional Publishing, 1999.
[31] J. L. Neto, A. Santos, C. Kaestner, and A. Freitas, “Document Clustering and Text Summarization,” Proceedings of the Fourth International Conference Practical Applications of Knowledge Discovery and Data Mining (PADD-2000), London, pp. 41-55, 2000.
[32] C. M. Wang, Web Search with Ontology-Supported Technology, Master Thesis, Department of Computer Science and Information Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, 2003.
[33] L.P. Jing, H. K. Huang, and H. B. Shi, “Improved Feature Selection Approach TFIDF in Text Mining,” Proceedings of the Machine Learning and Cybernetics, pp. 944-946, 2002.
[34] Y. L. OuYang, Study and Implementation of A Dialogued-Based Query System for Telecommunication FAQ Services, Master Thesis, Department of Computer and Information Science, National Chiao Tung University, Taiwan, 2000.
[35] G. Lebanon, “Metric Learning for Text Documents,” IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 28, no. 4, pp. 497-508, 2006.
[36] N. Guarino and P. Giaretta, Ontologies and Knowledge Bases: Towards a Terminological Clarification, Towards Very Large Knowledge Bases: Knowledge Building and Knowledge Sharing, Mars, N. (Eds.), IOS Press, Amsterdam, pp. 25-32, 1995.
[37] M. Uschold, and M. Gruninger, Ontologies: Principles, Methods, and Applications, The Knowledge Engineering Review, vol. 11, no. 2, pp. 93-136, 1996.
[38] G. Flouris, D. Plexousakis, and G. Antoniou, “Evolving Ontology Evolution,” Proceedings of the 32nd Int. Conference on Current Trends in Theory and Practice of Computer Science (SOFSEM 06), Merin, Czech Republic, pp. 14-29, 2006.
[39] R. Navigli, P. Velardi, and A. Gangemi, “Ontology Learning and Its Application to Automated Terminology Translation,” IEEE Intelligent Systems, vol. 18, no. 1, pp. 22-31, 2003.
[40] N. F. Noy and D. L. McGuinness, Ontology Development 101: A Guide to Creating Your First Ontology, Stanford Knowledge Systems Laboratory Technical Report KSL-01-05 and Stanford Medical Informatics Technical Report SMI-2001-0880, 2001.
[41] N.F. Noy and M. Klein, “Ontology Evolution: Not the Same as Schema Evolution,” Knowledge and Information Systems, vol. 6, no. 4, pp. 428-440, 2004.
[42] V. Tamma, S. Phelps, I. Dickinson, and M. Wooldridge, “Ontologies for Supporting Negotiation in E-commerce,” Engineering Applications of Artificial Intelligence, vol. 18, pp. 223-236, 2005.
[43] I. Spasic, S. Ananiadou, J. McNaught, and A. Kumar, “Text Mining and Ontologies in Biomedicine: Making Sense of Raw Text,” Briefings in Bioinformatics, vol. 6, no. 3, pp. 239-251, 2005.
[44] L. Yan, R. H. Wolniewicz, and R. Dodier, “Predicting Customer Behavior in Telecommunications,” IEEE Intelligent Systems, vol. 19, no. 2, pp. 50-58, March/April 2004.
[45] S. Rosset and E. Neumann, “Integrating Customer Value Considerations into Predictive Modeling,” Proceedings of the Third International Conference on Data Mining, pp. 283-290, 2003.
[46] KDnuggets, “Polls: Data Mining Methods (Mar 2007),” http://www.kdnuggets.com/polls/2007/data_mining_methods.htm, 2007.
[47] J. R. Quinlan, C4.5: Programs for Machine Learning, Morgan Kaufmann, San Mateo CA, 1993.
[48] J. R. Quinlan, “Induction of Decision Tree,” Machine Learning, vol. 1, pp. 81-106, 1983.
[49] F. Dehne, T. Eavis and A. Rau-Chaplin, “Computing Partial Data Cubes for Parallel Data Warehousing Applications,” Proceedings of Euro PVM/MPI’ 01, vol. 2131, LNCS, Springer Verlag, pp. 319-326, Santorini, Greece, Sep. 2001.
[50] T. Kohonen, “Self-Organized Formation of Topologically Correct Feature Maps,“ Biological Cybernetics, pp. 59-69, 1982.
[51] T. Kohonen, S. Kaski, K. Lagus, J. Salojarvi, J. Honkela, V. Paatero, and A. Saarela, “Self-Organization of a Massive Document Collection,” IEEE Transactions on Neural Networks, vol. 11, no. 3, pp. 574-585, 2000.
[52] M. Dittenbach, A. Rauber, and D. Merkl, “Uncovering Hierarchical Structure in Data using the Growing Hierarchical Self-Organizing Map,” Neurocomputing, vol. 48, pp. 199-216, 2002.
[53] M. Dittenbach, D. Merkl, and A. Rauber, “The Growing Hierarchical Self-Organizing Map,” Proceedings of the International Joint Conference on Neural Networks (IJCNN 2000), pp. 15-19, 2000.
[54] D. Merkl, M. Dittenbach, and A. Rauber, “Using Growing Hierarchical Self-Organizing Maps for Document Classification,” Proceedings of the 8th European Symposium on Artificial Neural Networks (ESANN'2000), Belgium, pp. 7-12, 2000.
[55] A. Rauber, M. Dittenbach, and D. Merkl, “Towards Automatic Content-based Organization of Multilingual Digital Libraries, Proceedings of the 3rd All-Russian Scientific Conference on Digital Libraries: Advanced Methods and Technologies, Digital Collections (RCDL2001), 2001.
[56] R. Agrawal and R. Srikant, “Fast Algorithms for Mining Association Rules,” Proceedings of the 20th International Conference on Very Large Databases, pp. 487-499, 1994.
[57] Z. Zheng, R. Kohavi, and L. Mason, “Real World Performance of Association Rule Algorithm,” Proceedings of the 7th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp.401-406, 2001.
[58] B. H. Chu, M. S. Tsai and C. S. Ho, “Toward a Hybrid Data Mining Model for Customer Retention,” Knowledge-Based Systems, vol. 20, issue 8, pp. 703-718, December 2007.
[59] B. H. Chu, K. C. Hsiao, and C. S. Ho, “An Intelligent Customer Retention System,” Proceedings of the 19th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems (IEA/AIE 2006), LNAI 4031, Annecy, France, pp. 1259-1269, June 2006.
[60] T. J. Gerpott, W. Rambs, and A. Schindler, “Customer Retention, Loyalty, and Satisfaction in the German Mobile Cellular Telecommunications Market,” Telecommunications Policy, vol. 25, pp. 249-269, 2001.
[61] H. S. Kin and C. H. Yoon, “Determinants of Subscriber Churn and Customer Loyalty in the Korean Mobile Telephony Market,” Telecommunications Policy, vol. 28, issue 9-10, pp. 751-765, 2004.
[62] Stanford Medical Informatics, “The Protégé Ontology Editor and Knowledge Acquisition System,” http://protege.stanford.edu.
[63] Chunghwa Telecom, “Best Package Plan Calculation,” http://www.cht.com.tw/PersonalCat.php?FCType=Mobile&CatID=695 &Module=Fee,Caculate.
[64] C.H. Tsai, “MMSEG: A World Identification System for Mandarin Chinese Text Based on Two Variants of the Maximum Matching Algorithm,” http://technology.chtsai.org/mmseg/.
[65] B. Liu, W. Hsu, and Y. Ma, “Integrating Classification and Association Rule Mining,” Proceedings of KDD’98, pp. 80-86, 1998.
[66] W. Li, J. Han, and J. Pei, “CMAR: Accurate and Efficient Classification Based on Multiple Class-Association Rules,” Proceedings of ICDM’01, pp. 369-376, 2001.
[67] C. C. Aggarwal, C. M. Procopiuc, and P. S. Yu, “Finding Localized Associations in Market Basket Data,” IEEE Transaction on Knowledge and Data Engineering, vol. 14, no.1, pp. 51-62, 2002.
[68] Q. Zou, W. Chu, J. David, and H. Chiu, “A Pattern Decomposition Algorithm for Data Mining of Frequent Patterns,” Knowledge and Information Systems, vol. 4, pp. 466-482, 2002.
[69] B. H. Chu, I. K. Liao, and C. S. Ho, “An Ontology-supported Database Refurbishing Technique and its Application in Mining GSM Trouble Shooting Rules,” Proceedings of the Ninth International Conference on Knowledge-based Intelligent Information and Engineering Systems (KES 2005), LNAI 3683, Springer-Verlag, pp. 997-1004, 2005.
[70] B. C. Liao, An Intelligent Proxy Agent for FAQ Service, Master Thesis, Department of Electronic Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, 2003.
[71] B. H. Chu, C. E. Lee, and C. S. Ho, “An Ontology-Supported Database Refurbishing Technique and its Application in Mining Actionable Troubleshooting Rules from Real-life Databases,” Engineering Applications of Artificial Intelligence, In Press.
[72] B. Liu, W. Hsu, and Y. Ma, “Mining Association Rules with Multiple Minimum Supports,” Proceedings of the Fifth ACM SIGKDD International Conference On Knowledge Discovery And Data Mining, pp. 337-341, 1999.
[73] C. L. Lui and F. L. Chung, “Discovery of Generalized Association Rules with Multiple Minimum Supports,” Proceedings of the 4th European Conference on Principles of Data Mining and Knowledge Discovery, vol. 1, pp. 510-515, 2000.
[74] M. C. Tseng and W. Y. Lin, “Mining Generalized Association Rules with Multiple Minimum Supports,” Proceedings of the Third International Conference on Data Warehousing and Knowledge Discovery, pp. 11-20, 2001.
[75] T. Joachims, A Probabilistic Analysis of the Rocchio Algorithm with TFIDF for Text Categorization, Technical Report CMU-CS-96-118, Department of Computer Science, Carnegie Mellon University, Pennsylvania, USA, 1996.
[76] B. H. Chu, A Graph-Theoretical Method for Verifying, Validating and Refining Constraint-Based Knowledge Bases, Master Thesis, Department of Electronic Engineering, National Taiwan University of Science and Technology, Taipei, Taiwan, 1995.
[77] B. Coppin, “Rules and Expert Systems,” in Artificial Intelligence Illuminated, Jones and Bartlett: Sudbury, MA, pp. 243-249, 2004.
[78] R. Barco, V. Wille, and L. Diez, “System for Automatic Diagnosis in Cellular Networks based on Performance Indicators,” European Transaction on Telecommunications, vol. 16, no. 5, pp. 399-409, 2005.
[79] R. Barco, L. Nielsen, R. Guerrero, G. Hylander, and S. Patel, “Automated Troubleshooting of a Mobile Communication Network using Bayesian Networks,” Proceedings of the 4th IEEE International Workshop on Mobile and Wireless Communications Network, pp.606-610, 2002.
[80] R. M. Khanafer, B. Solana, J. Triola, R. Barco, L. Moltsen, Z. Altman, and P. Lázaro, “Automated Diagnosis for UMTS Networks Using Bayesian Network Approach,” IEEE Transactions on Vehicular Technology, vol. 57, no. 4, pp. 2451-2461, 2008.
[81] S. Munagala, L. Moltsen, R. Barco, and P. Lázaro, “Automated Troubleshooting of Satellite Communication Ground Equipment,” Proceedings of IEEE Conference on Aerospace, pp. 1-10, March 2008.
[82] A. Samhat, R. Skehill, and Z. Altman, “Automated Troubleshooting in WLAN Networks,” Proceedings of the16th Mobile and Wireless Communications Summit, pp.1-4, 2007.
[83] D. Tikunov and T. Nishimura, “Automated Troubleshooting of Mobile Networks based on Alarm and Performance data using Bayesian Networks,” Proceedings of the 15th International Conference on Software, Telecommunications and Computer Networks (SoftCOM 2007), pp. 1-5, Sept. 2007.