臺灣博碩士論文加值系統

在21世紀的知識經濟時代，知識的創造、流通、加值、分享及再利用，已經成為目前經濟活動的原動力，因此對業者而言取得決策的商情知識是一件刻不容緩的事，它可以幫助企業在競爭激烈且瞬息萬變的環境中掌握競爭優勢。研究指出企業的管理者及決策者他們最迫切及最希望取得的商情知識，首要就是與顧客相關的知識，再者就是與市場經營相關的知識。而流通零售業是台灣當前的明星產業，加上電子商務的推波助瀾之下，資訊的即時性和通透性就更顯重要，因此我們就以流通零售業態中的便利商店和連鎖超市進行商情知識發現的研究。
便利商店在三十幾坪的賣場裡，每天進入門市消費的顧客平均七至八百人次，所帶來的商機實不容小覷。面對每天來來往往形形色色的顧客，對商店內上千種的產品各有其不同的偏好，因而衍生出不同的消費習慣，是以業者欲掌握商機，需首重顧客消費行為的了解，方能據以進行目標行銷，以提高銷貨量及顧客滿意度，使業者的利潤最大化。為此，本研究將以國內某知名便利商店為對象，導入知識發現方法論，由顧客消費交易記錄的原始資料，運用資料探勘中關聯性法則的技術，依消費時間與客層別屬性分析不同時段以及不同性別、年齡層顧客的特徵，試圖挖掘出有意義的知識法則，並做消費行為的深入分析與探討。在研究過程中，我們特別專注於克服資料量不足的議題上。實證結果顯示，經由適當工具的應用以及領域專家知識的經驗分享，仍可在有限的資料中，有效地找出隱藏的珍貴商情知識。
連鎖超市其營業所分處於不同的地理區域，有各自的商圈和特性，因此我們必須針對市場進行市場區隔。由於來源資料庫裡的關聯表記錄結構性低且數量龐大，所以將各個歷史資料表彙總，先期建置商業資料倉儲，再導入知識發現方法論，運用資料歸納、分類與分群的資料探勘技術，以區域、類別、時間三個維度，進行挖掘並深入分析探討。並建置一流通業知識管理決策支援的線上系統，提供決策者友善且彈性的操作界面，可以即時取得適時、適地的商情知識；協助業者能早一步洞悉市場的情勢及動向，有充裕的反應時間即早準備並擬定策略，而在競爭市場取得先機。

The 21st century is a knowledge-intensive society, the creation of knowledge, its distribution, value adding, channeling and re-use have already become the engine of growth for the economy. Hence, the acquisition of marketing plan and business intelligence is of utmost urgency and importance for the businessman. Research has indicated that the most critical and important market intelligence and information that decision maker and operational executive of an enterprise are looking for is the information on customers and the information related to market operation as well. In this thesis, we focus on the convenient stores sector and super market chain sector within the distribution and retail industry to facilitate the study on market intelligence and knowledge discovery.
Convenient stores are 700 to 800 customers on average stop by each store everyday to buy things and the business opportunity presented thus should not be underestimated or ignored. The operators of the convenient stores must be able to gather enough information pertaining to customers preference, habits, wants and demands in order to make targeted promotion of certain popular items and increase more sales volume and improve customer satisfaction, this will in turn maximize the profits of the operators. In this study, we conduct a case study on a famous convenient store chains in Taiwan and apply the overwhelming knowledge discovery methodology to achieve the research goal. We perform association rule discovery to uncover the hidden patterns from the raw data and by analyzing the time of purchase and consumer characteristics of the sales data, we can differentiate sales data according to the consumer''s sex, age, time of purchase and consumer demographics. The experimental results demonstrate that the derived useful knowledge from the information can help the store study analyze consumer behavior in depth. In this study, we pay special attention to the issue of overcoming the problem of insufficient data. The practical experiment has proven that by using suitable tools and consulting experienced experts in specialized fields to analyze the data, one still can extract valuable market intelligence and useful information hidden in the limited of data.
Supermarket chains that are located in different geographical areas has their own market domain and unique characteristics, hence we have to differentiate the different markets by using market segmentation. In the second part of this thesis, we apply classification and clustering techniques in data mining to analyze and probe deeply through the dimension of zone, product class and time of the transaction database. Since the relation table of the database has a lot of unstructured data records, we first aggregate the history tables and build up the data warehouse, then construct a Web-based decision support system in which the model base is supported by the outcomes of the warehousing and mining. The decision support system provides decision makers a friendly and flexible interface to acquire real-time and on—the-spot business intelligence and information, obtain an early feeling of the market direction and situation, to have adequate time to make timely preparation and formulate strategy in order to gain initiative and an edge in the market competition.

壹、 緒論1
一、 研究背景1
二、 研究動機1
三、 研究目的2
四、 研究限制4
五、 研究流程5
貳、 文獻探討8
一、 知識管理8
(一) 知識的定義與分類8
(二) 知識管理的定義與目的10
二、 知識發現與資料探勘11
三、 資料探勘模式12
四、 資料探勘在流通零售業的相關研究16
參、 研究方法19
一、 流通零售業的概述19
(一) 顧客消費模式知識之探勘22
(二) 市場商情知識之探勘23
二、 知識管理的相關探討24
(一) 知識管理的範疇24
(二) 知識的操作程序26
(三) 知識發現與創新28
(四) 知識組織與儲存29
(五) 知識分享30
(六) 知識應用31
三、 知識發現的理論基礎與方法32
(一) CRISP-DM 資料探勘方法論32
(二) 資料倉儲(Data warehouse)35
(三) 知識發現法與資料探勘技術37
(四) 關聯法則(Association Rules)40
(五) 資料歸納技術(data generalization)44
(六) 分類技術(classification)48
四、 研究架構52
肆、 顧客消費模式知識之探勘57
一、 前言57
二、 流通零售業的需求與問題探討58
三、 建立目標資料59
四、 資料前置處理60
(一) 刪除資料庫中不重要的欄位60
(二) 各屬性值的處理60
(三) 資料轉換61
五、 探勘模式的選擇與建立61
六、 資料探勘－挖掘商品項目關聯法則63
(一) 關聯法則的應用63
(二) 探勘結果的分析與評估65
七、 資料探勘－時間屬性抽象化67
(一) 實驗設計一68
(二) 實驗設計二70
八、 資料探勘－顧客特徵72
(一) 性別屬性73
(二) 探勘結果的分析與評估(性別)74
(三) 年齡屬性(壯年)75
(四) 探勘結果的分析與評估(年齡)75
(五) 性別及年齡屬性76
(六) 探勘結果的分析與評估(性別&年齡)77
九、 結論78
伍、 市場商情知識之探勘80
一、 前言80
二、 流通零售業的需求與問題探討82
三、 建立目標資料集82
四、 資料前置處理84
五、 探勘模式的選擇與建立88
六、 資料探勘－OLAP90
(一) 探勘模式設計90
(二) 區域別的分析與評估93
(三) 商品類別的分析與評估95
(四) 區域與商品類別的交互分析96
(五) 小結98
七、 資料探勘－樞紐分析表98
(一) 商品週銷售走勢分析99
(二) 大銷售量商品分析100
八、 資料探勘－屬性導向歸納法102
(一) 探勘模式設計102
(二) 探勘模式的實作104
(三) 實驗結果的分析與評估106
九、 資料探勘－分類技術107
(一) 探勘模式設計與實現107
(二) 探勘結果的分析110
(三) 探勘模式的評估與應用113
十、 結論115
陸、 結論與未來展望117
一、 研究成果與結論117
(一) 顧客消費模式知識探勘的成果118
(二) 市場商情知識探勘的成果120
二、 研究貢獻122
三、 未來研究建議123
參考文獻125
附錄一133
附錄二141
簡歷146

1.Davenport, T. H. and Prusak, L. (胡瑋珊譯) ，2000， 知識管理，中國生產力。2.Gates, B., 1999, 樂為良譯，“數位神經系統：與思考等快的明日世界”，商業周刊。3.方世榮，1996，行銷學，台北：三民書局。4.吳思華，1996，策略九說，台北：麥田出版社。5.吳靄書，1995，現代零售管理，大中國圖書股份有限公司，頁1~26。6.李孟熹，1995，實戰零售學(上)零售業行銷策略，群泰企管公司叢書，頁2~10。7.李昇暾，2001，”以資料採研深化顧客關係管理”，遠擎期刊，遠擎管理顧問公司出版，頁99-111。8.村上豐道，1998，7-ELEVEN大革命，大展出版社有限公司。9.沈清正、陳仕昇、高鴻斌、張元哲、陳家仁、黃琮盛、陳彥良，2002，”資料間隱含關係的挖掘與展望”，資訊管理學報，9卷，專刊期。10.沈維明，2000，應用資料挖掘於目標行銷之研究，私立輔仁大學資管系，碩士論文。11.林文修, 1997, “Data Mining探索(上)(下)”, 叡陽資訊經營決策論壇，第13、14期。12.林琪淵，2000，在POS資倉儲中挖掘關聯規則，國立中央大學資管系，碩士論文。13.邵敏華，1997，建構開放性之企業知識管理系統－以行銷公司為例，國立政治大學資管系，碩士論文。14.胡運沛，2000，探勘交易觸發事件與消費特徵，國立雲林科技大學資管系，碩士論文。15.張瑋倫，2000，應用資料挖掘學習方法探討顧客關係管理問題，私立輔仁大學資管系，碩士論文。16.曾守正，1997，“從想像中找出事實：如何讓Data Mining成為企業的一部分？”，資訊與電腦，12月，頁82-84。17.曾守正、周韻寰，1999，資料庫系統進階實務，儒林圖書有限公司，頁8-1 ~8-97。18.黃彥文，2000，資料探勘之應用 - 會員消費特徵之發掘，國立屏東科技大學資管系，碩士論文。19.勤業管理顧問公司著(劉京偉譯)，2000，知識管理的第一本書，商周出版。20.楊亨利、郭家佑，2000，”資料庫中空間性週期關聯規則之發掘-以便利商店交易資料為例”，中華管理評論，3卷，7期，3月，頁99~121。21.廖啟揚，2002，”2002年台灣地區零售通路營運走向分析報告”，零售市場雜誌，381期，2月。22.緒方知行，1995，7-Eleven物語，時報文化出版企業有限公司。23.Adriaans, P. and Zantinge, D., 1996, Data Mining, Addison Wesley Longman.24.Aggarawal, C. and Yu, P., 1998, “A New Framework for Itemset Generation”, Proceedings of the ACM PIOS.25.Agrawal, R., et al., 1993, “Mining Association Rules between Sets of Items in Large Databases”, Proc. of the ACM SIGMOD 1993 International Conference on Management of Data, May, pp. 207-216.26.Agrawal, R. and Srikant, R., 1994,”Fast Algorithms for Mining Association Rules”, Proc. of the Int''l Conf. Very Large Data Bases, pp. 487-499.27.Agrawal, R. and Srikant, R., 1995, “Mining Sequential Patterns”, Proc. of the Int’1 Conference on Data Engineering (ICDE), Taipei, Taiwan, March.28.Agrawal, R., et al., 1996, “The Quest Data Mining System”, Proceedings of the Int’l Conference on Knowledge Discovery in Databases and Data Mining, Portaland, Oregon, August.29.Berry, M. A. and Linoff, G. S., 2000, Mastering Data Mining: The Art & Science of Customer Relationship Management, John Wiley & Sons, Inc.30.Berson, A. and Smith, S. J., 1997, Data Warehousing, Data Mining, and OLAP, McGraw-Hill.31.Bock, F., 1998, “The Intelligent Organization”, Arthur D. Little PRISM, Second Quarter.32.Brachman, R. J., et al., 1996, “Mining Business databases”, Communications of the ACM, Vol. 39, No. 11, Nov., pp. 42-48.33.Breiman, L., et al., 1984, Classification and Regression Tree, Wadsworth, Belmont, CA.34.Brin, S, Motwani, R. and Silverstein, C., 1997a,”Beyond Market Baskets: Generation Association Rules to Correlations”, Proceeding of the ACM SIGMOD International Conference on Management of Data, pp. 265-276.35.Brin, S, et al., 1997b,”Dynamic Itemset Counting and Implication Rules for Market Basket Data”, Proceeding of the ACM SIGMOD International Conference on Management of Data, pp. 255-264.36.Carter, C. L. and Hamilton, H. J., 1995, “A Fast, On-Line generalization Algorithm for Knowledge Discovery”, Applied Mathematics Letters, Vol. 8, Issue: 2, March, pp. 5-11. 37.Carter, C., Hamilton, H. and Cercone, N., 1997, “Share Based Measures for Itemsets”, Principles of Data Mining and Knowledge discovery, J. Komorowski and J. Zytkow (Eds.), pp. 14-24.38.Chen, M.S, Han, J. and Yu, P. S., 1996, “Data Mining: An Overview from a Database Perspective”, IEEE Transactions on Knowledge and Data Engineering, Vol. 8, No. 6, Dec., pp. 866-883.39.Cheung, D. W., et al., 1996, “A Fast Distributed Algorithm for Mining Association Rules”, Proc. of the 1996 Int’l Conf. On PDIS’96, Miami Beach, Florida, USA, Dec.40.Cheung, D. W., Lee, S. D. and Kao, B., 1997, " A General Incremental Technique for Maintaining Discovered Association Rules," Proceedings of the Fifth International Conference On Database Systems For Advanced Applications (DASFAA ''97), Melbourne, Australia. March.41.Clark, P. and Niblett, T., 1989, “The CN2 Induction Algorithm”, Machine Learning, Vol. 3, pp. 261-283.42.Codd, E. F., Codd, S. B. and Salley, C. T., 1993, “Providing OLAP (On-Line Analytical Processing) to User Analysts: An IT Mandate”, White Paper, Arbor Software Corporation.43.Davenport, T. H. et al., 1998, “Successful Knowledge Management Projects”, Solan Management Review, Vol.39, pp. 43-57.44.Dawson, R., 2000, Developing Knowledge-Based Client Relationships: The Future of Professional Services, Butterworth — Heinemann, Boston.45.Fayyad, U.M., et al., 1996, “ Advances in Knowledge Discovery and Data Mining”, AAAI Press/The MIT Press, Menlo Park.46.Fayyad, U.M., Shapiro, G. P. and Smyth, P., 1996a, “From data Mining to Knowledge Discovery: An Overview”, Advances in Knowledge Discovery and Data Mining, MA AAAI/ MIT Press, pp. 1-36. 47.Fayyad, U.M., Shapiro, G. P. and Smyth, P., 1996b, “The KDD Process for Extracting Useful Knowledge from Volumes of Data”, Communications of the ACM, Vol. 39, No. 11, pp. 27-34. 48.Fu, Yongjina, 1996, ”Discovery of Multiple-Level Rules from Large Databases”, Ph. D. dissertation, Simon Fraser University.49.Gresten, W, Wirth, R. and Arndt, D, 2000, ”Predictive Modeling in Automotive Direct Marketing: Tools, Experiences and Open Issues”, KDD 2000, pp. 398-406.50.Gundry J. and Metes G., 1998, “Team Knowledge Management”, A Computer Mediated Approach, Sep.51.Ha, S. H. and Park, S. C., 1998, “Application of Data Mining Tools to Hotel Data Mart on the Intranet for Database Marketing”, Expert Systems With Applications, Vol. 15, pp. 1-31.52.Han, J., Cai, Y. and Cercone, N., 1991, “Attribute-Oriented Induction in Relational Databases”, Knowledge Discovery in Databases, pp. 213-228.53.Han, J., Cai, Y. and Cercone, N., 1992, “Knowledge Discovery in Database: An Attributed-Oriented Approach”, Proceeding of the 18 International Conference on Very Large Data Bases, pp. 547-559.54.Han, J., Cheung, D. W. and Fu, A. W., 1994, “Knowledge Discovery in Database: A Rule-Based Attribute-Oriented Approach”, proc. of the 8 International Sympsium on Methodologies for Intelligent Systems, pp. 164-173.55.Han, J. and Fu, Y., 1995, “Discovery of Multiple-Level Association Rules from Large Databases”, 1995 Int. Conf. Very Large Database, Sept., pp.400-431.56.Han, J., et al., 1995a, “Advances of the DBLearn System for Knowledge discovery in Large Databases”, Proc. of 1995 Int’l Joint Conf. on Artificial Intelligence (IJCAI’95), Montreal, Canada, Aug, pp. 2049-2050.57.Han, J., 1998, “Towards On-Line Analytical Mining in Large Databases”, ACM SIGMOD RECORD, Vol. 27, No.1, Mar., pp. 97-107.58.Han, J. and Kamber, M., 2001, Data Mining Concepts and Techniques, Academic Press.59.Harris, D. B., 1996, “Creating a Knowledge Centric Information Technology Environment”, September.60.Hasan, H. and Hyland, P., 2001, “Using OLAP and Multidimensional Data for Decision Marking”, IT Pro.61.Hedlund, G., 1994, “A Model of Knowledge Management and the N-Form Corporation”, Strategic Management Journal, Vol. 15, pp. 73-90.62.Hiderman, R. J., et al., 1996, “Data Mining with Concept Generalization Graphs”, In Proceedings of the Ninth Annual Florida AI Research Symposium, Key West, Florida, May.63.Hilderman, R. J., Hamilton, H. J. and Barber, B, 1999, “Ranking the Interestingness of Summaries from Data Mining Systems”.64.Hipp, J., Guntzer, U. and Nakhaeizadeh,G. , 2000, “Algorithms for Association Rule Mining — A General Survey and Comparison “, ACM SIGKDD, Vol. 2, pp. 58-64.65.Hope, J. and Hope, T, 1997, “Competing In the Third Wave: The Ten Key Management Issues of the Information Age”, Harvard Business School Press.66.Hoven, J. V. D., 1998,”Data Warehousing: Bringing It All Together”, Information System Management, Spring, pp. 92-95.67.Inmon, W. H., 1993, Building Data Warehouses, John Wiley and Sons.68.Inmon, W. H., and Hackathorn, R. D., 1994, Using The Data Warehouse, John Wiley and Sons.69.Karlenzig, W., 2000, “What KM Really Contributes to E-Business”, Knowledge Management Magazine3, Vol. 1, No. 14.70.Kennedy, R. L., et al., 1998, Solving Data Mining Problems through Pattern Recognition, Unica Technologies Inc.71.Kimball, R., 1996, The Data Warehouse Toolkit, John Wiley & Sons, New York.72.Klemettinen, M. Mannila, H. and Verkamo, A. I., 1999, “Association Rule Selection in a Data Mining Environment”, PKDD-99, pp. 372-377.73.Liu, B., et al., 1998, “Visually Aided Exploration of Interesting Association Rules”, National University of Singapore.74.Mantaras, R. L., 1991, "A Distance-Based Attribute Selection Measure for Decision Tree Induction," Machine Learning 6, pp. 81-92.75.Murtaza, A., 1998,”A framework for Developing Enterprise data Warehouse”, Information System Management, Fall, pp. 21-26.76.Nonaka, I. And Takeuchi, H., 1991, “The Knowledge-Creating Company”, Harvard Business Review, November-December, pp. 2-9.77.Nonaka, I., 1994, “A Dynamic Theory of Organizational Knowledge Creation”, Organization Science, Vol. 5, No. 1, pp. 14-37.78.Nonaka, I. And Takeuchi, H., 1995, The Knowledge-creating Company, New York, Oxford.79.Nonaka, I., Umemoto, K. and Senno, D., 1996, “From Information Processing to Knowledge Creation: A Paradigm Shift in business Management”, Technology in Society, Vol. 18, No. 2, pp. 203-218.80.Park, J. S., Chen, M. S. and Yu, P. S., 1995, “An Effective Hash Based Algorithm for Mining Association Rules”, Proc. of ACM SIGMOD, May 23-25, pp. 175-186.81.Park, J. S., Chen, M. S. and Yu, P. S., 1997,”Using a Hash-Based Method with Transaction Trimming and Database Scan Reduction for Mining Association Rules”, IEEE Trans. On Knowledge and Data Engineering, Vol. 9, No. 5, October, pp. 813-825.82.Piatesky — Shapiro, G. and, Frawley, W. J., 1991, “Knowledge Discovery in Database”, AAAI Press/ The MIT Press: Cambridge, MA.83.Pork, J. S., Chen, M. S. and Yu, P. S., 1995, “An Effective Hash Based Algorithm for Mining Association Rules”, ACM SIGMOD, May, pp. 175-186.84.Puzzanghera, P., 1999, “The bigger picture ”, Intelligent Enterprise MAR, pp.39.85.Quinlan, J. R., 1979, “Discovering rules from large collections of examples: a case study”, In Michie, D., editor, Expert Systems in the Microelectronic Age. Edinburgh University Press, Edinburgh Scotland.86.Quinlan, J.R., 1986, “Induction of Decision Tree”, Machine Learning, Vol.1, pp.81-106.87.Quinlan, J. R, 1993, “C4.5: Programs for Machine Learning”, Morgan Kaufmann, San Mateo, CA.88.Quinn, J. B., Anderson, P. and Finkelstein, S., 1996, “Managing Professional Intellect: Marking the Most of the Best”, Harvard Business Review, March-April, pp. 71-80.89.Savasere, A., Omiecinski, E. and Navathe, S., 1995, "An Efficient Algorithm for Mining Association Rules in Large Databases," Proc. Int''l Conf. Very Large Data Bases, Zurich, Switzerland, Sept, pp. 432-444.90.Savasere, A., Omiecinski, E. and Navathe, S., 1998, “Mining for Srong Negative Associations in A Large Database of Customer Transactions”, Proc. of the 14th International Conference on Data Engineering, Feb., pp. 494-502.91.Shaw, M.J., et al., 2001, “Knowledge management and data mining for marketing”, Decision Support Systems, Vol.31, pp.127-137.92.Smith, R. G. and Farquhar A., 2000, “The Road Ahead for Knowledge Management An AI Perspective”, AI MAGAZINE, pp. 17-40.93.Spek, R. V. and Spijkervent, A., 1997, “Knowledge Management: Dealing Intelligently with Knowledge”, Knowledge Management and It’s Integrative Elements, edited by Liebowitz, J. and Wilcox, L. C., CRC Press, New York, pp. 31-59.94.Sung, H. H. and Sang, C. P., 1998, “Application of Data Mining Tools to Hotel Data Mart on the Internet for Database Marketing”, Expert Systems with Applications, Vol.15, No.1, Jul., pp. 1-31.95.Umanol, M., et al., 1994, “Fuzzy decision trees by fuzzy ID3 algorithm and its application to diagnosis systems”, Proceedings of the Third IEEE Conference, Vol. 3, pp.2113 —2118.96.Vassiliadis, P. and Sellis, T., 1999, “A Survey of Logical Models for OLAP Databases”, SIGMOD Record, Vol. 28, No.4, pp. 64-69.97.Weiss, S. M. and Indurkhya, N., 1996, “Decision Tree Pruning: Biased or Optimal? ”, AAAI-96/MIT, pp. 626-632.98.Wiig, K. M., 1995, “Knowledge Management Foundations: Thinking about Thinking”, Schema Press, Texas.99.Zaki, M. J. et al., 1997, “New Algorithms for Fast Discovery of Association Rules”, American Association for Artificial Intelligence (www.aaai.org).100.Zhang, S., et al., 1998,“A Mining Model Based on Piatesky-Shapiro’s Argument”.