現今企業競爭激烈，企業為了能永續經營，不斷的縮短產品開發時間外，也需要能快速反應顧客需求，所以企業也開始瞭解與滿足顧客的需求，與顧客建立良好關係，以往企業只重視實體產品，但現在也逐漸重視無形的服務，希望藉著提高服務品質，來提高顧客滿意度，以提高競爭力。所以企業開始透過產品的特性來設計服務內容，利用服務內容來提高顧客的保留率及市場佔有率。因此透過提供服務所產生的價值與內容的重要性，慢慢的逐漸超過有形的實體產品。
近年來網際網路蓬勃發展，導致服務資訊超載，為了讓顧客有效找到符合之服務資訊，因此出現了很多提供搜尋功能的系統，但目前的系統大部分都以產品導向，以產品之特徵為篩選的依據。但遺忘了服務的重要性及忽略了與顧客使用服務時所產生的價值為搜尋的重點。因此本研究以服務價值為推薦之依據，來提高所推薦服務的價值
所以本研究希望建立一個以服務為主的推薦系統，藉由RFM模型以分析出重要顧客名單及最有價值服務項目，然後用關聯規則探勘出，與最有價值服務項目之關聯性強的服務項目以推薦給顧客。為了來驗證此推薦系統之可行性及所推薦的服務項目是否符合顧客所需，本研究將所蒐集到的旅遊業資料，透過三個實驗『運用RFM模型分析顧客使用服務喜好』、『運用RFM模型分析顧客使用服務項目』、『運用關聯規則來產生有價值的服務項目之推薦清單』，分析出重要顧客名單，並推薦有價值的服務項目清單給顧客。
然後為了評估本研究的推薦系統的效能，以使用精確率(Precision)、回應率(Recall)與Fallout這三項指標來做評估，同時，本研究與關聯規則之Apriori演算法進行比較分析。由實驗結果顯示，本研究所建立的推薦系統的精確率、回應率及Fallout指標都大於傳統Apriori演算法，因此表示本研究之推薦系統能推薦具高價值的服務。
由實驗可得知，本研究透過RFM模型分析，將服務價值加以量化且保留下來，並且透過推薦系統來分享給下一位顧客。且可以針對不同行業領域來設定其服務項目，而所設定的服務項目可以跨領域性，不單單只有單一領域的推薦，以減少顧客的搜尋成本。而本研究所建立的推薦系統可以適用於不同的行業，將個別行業的服務項目設定於系統中，不會只侷限於旅遊業。
因為本研究實驗是套用國內旅遊業，而未加入國內旅遊業所重視的因素，加以調整相關權重比例，而未來的研究以此為基礎，來探討不同領域，或是結合不同領域，將不同領域所重視的因素加入，也可以根據領域上所重視的元素來調整參數的權重，然後也可以依據不同領域來設計可能創造出來的服務價值，讓所推薦之服務項目能更準確地符合顧客的需求，創造出更多元的服務項目。

Services have been important role to perform economic activities. In order to fulfill customer needs and increase customer retention and loyalty, enterprises attempt to design high quality services by considering good features. With the development of Internet, service information overloading becomes an essential issue nowadays. There are existing recommendation systems to help customers to find suitable information. However, these systems are built based on the product perspective rather considering values of services. Hence, this study aims to develop a service recommendation system to increase quality of services.     
The service recommendation system is to find out the list of key customers and the list of key service items by applying the RFM and association rules approaches. Accordingly, this study conducts three experiments to verify the feasibility of the service recommendation system and evaluate the suitability of recommended services. Meanwhile, this study also uses Precision, Recall and Fallout to assess the performance of the service recommendation system by comparing to the mechanism of Apriori algorithm. The results show that the service recommendation system has higher performance than the mechanism of Apriori algorithm.    
The research contributions are addressed as follows. Service values can be numerically represented and preserved via the RFM analysis. Valuable services are first to serve customers. The service recommendation system can be applied into different fields by defining suitable services in order to decrease searching cost. Finally, researchers can extend our system by considering other factors in different industries and defining proper weights to provide customers with high quality services for the further research.

目錄
謹誌	I
目錄	VI
1.1研究背景	1
1.2研究動機	3
1.3研究問題	4
1.4研究目的	6
1.5研究架構	8
第貳章 文獻探討	10
2.1服務科學(Service Science)	10
2.2最近消費時間、使用頻率、消費金額(Recency 、Frequency 、Monetary )	15
2.3關聯規則(Association Rules)	21
第參章 研究方法	29
3.1系統架構	30
3.2 RFM 模型分析	33
3.3 關聯規則分析(Association Rules Analysis)	44
第肆章實驗分析	50
4.1 實驗資料來源	51
4.2實驗程式語言與工具	51
4.3顧客旅遊資訊分析	52
4.4實驗一：運用RFM模型分析顧客使用服務喜好	53
4.5實驗二：運用RFM模型分析顧客使用服務項目	60
4.6實驗三：運用關聯規則產生服務項目推薦清單	67
4.7實驗四：評估推薦效能評估	69
4.8 討論與發現	72
第伍章 結論	75
5.1結論	75
5.2研究貢獻	76
5.4研究限制與範圍	78
5.5未來研究	78
參考文獻	80
 
表目錄
表2-1資料探勘基於RFM值的研究	20
表2-2運用資料探勘技術找出關聯規則的研究	27
表4-1顧客旅遊資訊(僅列舉部分資料)	53
表4-2顧客旅遊紀錄表	54
表4-3 顧客RFM 表  55
表4-4 顧客五等分RFM 表  56
表4-5顧客RFM	57
表4-6RFM五等分轉換對照表(服務喜好101)	58
表4-7RFM五等分轉換對照表(服務喜好103)	58
表4-8顧客五等分RFM	59
表4-9服務喜好之重要顧客數量表	60
表4-10顧客服務項目紀錄表	61
表4-11服務項目RFM表	62
表4-12服務項目五等分RFM表	63
表4-13服務項目RFM	64
表4-14服務喜好101之服務項目RFM五等分轉換對照表	65
表4-15服務喜好102之服務項目RFM五等分轉換對照表	65
表4-16服務項目五等分RFM	66
表4-17服務喜好之有價值服務項目表	67
表4-18顧客服務項目使用紀錄表	68
表4-19服務項目推薦清單	69
表4-20研究與Apriori推薦實驗之推薦效能結果	72
 
圖目錄
圖1-1論文架構	9
圖2-1產生高頻項目集之演算法過程	24
圖2-2 Apriori 演算法案例	26
圖3-1服務推薦系統處理流程	30
圖3-3顧客喜好RFM模型分析處理過程	33
圖3-4顧客服務喜好RFM模型分析處理過程	34
圖3-5顧客服務喜好RFM模型分析之系統架構	36
圖3-6 重要顧客RFM 演算法	38
圖3-7 顧客服務項目RFM分析	39
圖3-8顧客服務項目RFM模型分析之系統架構	40
圖3-9 有價值服務項目RFM 演算法	43
圖3-10服務關聯規則分析處理過程	44
圖3-11服務關聯規則分析之系統架構	45
圖3-12Apriori演算法	48
圖4-1實驗程式所運用技術之架構	52

參考文獻
[1] 中央研究院人心調查研究專題中心，<國人旅遊狀況調>，網址：https://srda.sinica.edu.tw/，上網日期：2016年5月31日
[2] R.F.Lusch、S.L.Vargo、G. Wessels, < Toward a conceptual foundation for service science: Contributions from service-dominant logic>, IBM Systems Journal, vol.47, no.1, pp.5-14, 2008.
[3] Stephen L.Vargo、Melissa Archpru Akaka,<Service-Dominant Logic as a 	Foundation for Service Science:Clarifications>, Service Science, vol.1, no.1, pp.32-41, 2009
[4] Richard Normann, <Reframing Business : When the Map Changes the Landscape>, Jossey-Bass,2001.
[5] Paul P.Maglio、Jim Spohrer,< Fundamentals of service science>, Journal of the Academy of Marketing Science,vol.36, no.1, pp.18-20, 2008
[6] Valarie A.Zeithaml, <Consumer perceptions of price, quality, and value: A means-end model and synthesis of evidence>, The Journal of	Marketing,vol.52,pp.2-22,1998
[7] Ruth N.Bolton、James H.Drew, <A multistage model of customers' assessments of service quality and value>, Journal of Consumer Research, vol.17, no.4, pp.375-384, 1991.
[8] Robert B. Woodruff, <Customer value: The next source of competitive advantage>, Journal of the Academy of Marketing Science, vol.25, no.2, pp.139-153, 1997.
[9] Rakesh Agrawa、Tomasz Imielinski、Arun Swami,< Mining association rules between sets of items in large databases.>,  ACM SIGMOD Record, vol.22, no.2, pp.207-216, 1993.
[10] Anand, N.、Gardner, H. K.、Morris, T., < Knowledge-based innovation: Emergence and embedding of new practice areas in management consulting firms>, Academy of Management Journal, vol.50, no.2, pp.406-428, 2007.
[11] Bult、J. R.、Wansbeek, T., <Optimal selection for direct mail>, arketing Science, vol.14,no.4,pp. 378-394,1995.
[12] Chang, H.、Tsai, H., <Group RFM analysis as a novel framework to discover better customer consumption behavior>, Expert Systems with Applications, vol.38, no.12,
pp.14499-14513, 2011.
[13] Chen, R., <RFM-based eco-efficiency analysis using Takagi–Sugeno fuzzy and AHP approach>, Environmental Impact Assessment Review, vol.29, no.3, pp.157-164, 2009
[14] Chen, Y、Kuo, M、Wu, S、Tang, K, < Discovering recency, frequency, and monetary (RFM) sequential patterns from customers’ purchasing data>,  Electronic Commerce Research and Applications vol.8, no.5, pp.241-251, 2009.
[15] Cheng, C.、Chen, Y, <Classifying the segmentation of customer value via RFM model and RS theory>, Expert Systems with Applications, vol.36, no.3, pp.4176-4184, 2009.
[16] Cheng, L、Sun, L, <Exploring consumer adoption of new services by analyzing the behavior of 3G subscribers : An empirical case study>, Electronic Commerce Research and Applications, vol.11, no.2, pp.89-100, 2012. 
[17] Chiang, W, <To mine association rules of customer values via a data mining procedure with improved model: An empirical case study>, Expert Systems with Applications ,vol.38, no.3, pp.1716-1722, 2011. 
[18] Cho, Y. H.、Kim, J. K, <Application of web usage mining and product taxonomy to collaborative recommendations in e-commerce>, Expert Systems with Applications ,vol.26, no.2, pp.233-246,  2004. 
[19] Demirkan, H、Goul, M., < Service oriented technology management to improve organizational agility>, International Journal of Innovation and Technology Management, vol.6, no.01, pp.1-16, 2009. 
[20] Dominguez-P&eacute;ry, C.、Ageron, B、Neubert, G, <A service science framework to enhance value creation in service innovation projects.an RFID case study>, International Journal of Production Economics, vol.141, no.2, pp.440-451, 2013 
[21] Ernst, H., <Success factors of new product development: A review of the empirical literature>. International Journal of Management Reviews, vol.4, no.1, pp.1-40, 2002. 
[22] Glushko, R. J, < Designing a service science discipline with discipline>, IBM Systems Journal, vol.47, no.1, pp.15-27, 2008. 
[23] Groth, R, <Data mining: Building competitive advantage>, Prentice Hall PTR., 2000 
[24] Han, J.、Kamber, M.、Pei, J, <Data mining: Concepts and techniques>, Morgan kaufmann, 2006. 
[25] Hosseini、S. M. S、Maleki, A、Gholamian、M. R, <Cluster analysis using data mining approach to develop CRM methodology to assess the customer loyalty>,Expert Systems with Applications, vol.37, no.7, pp.5259-5264, 2010
[26] Huang, S、Chang, E、Wu, H., <A case study of applying data mining techniques in an outfitter’s customer value analysis>, Expert Systems with Applications, vol.36, no.3, pp.5909-5915, 2009
[27] Hughes, A. M, <Strategic database marketing>, McGraw-Hill Pub.Co, 2005.
[28] Joo, Y. G、Sohn、S. Y, <Structural equation model for effective CRM of digital content industry>, Expert Systems with Applications, vol.34, no.1, pp.63-71, 2008 
[29] Kaymak, U, < Fuzzy target selection using RFM variables>,IFSA World Congress and 20th NAFIPS International Conference, Joint 9th ,2, pp.1038-1043, 2001  
[30]Koch、R, <The 80/20 principle: The secret to achieving more with less >, Random House LLC, 2011.
[31] Liao, S.、Chen, Y.、Deng, M, <Mining customer knowledge for tourism new product development and customer relationship management>, Expert Systems with Applications, vol.37, no.6, pp.4212-4223, 2010
[32] Lin, W、Alvarez、S. A.、Ruiz, C, < Efficient adaptive-support association rule mining for recommender systems>, Data Mining and Knowledge Discovery,vol.6, no.1, pp.83-105, 2002 
[33] Linoff, G. S.、Berry, M、J.Mining, <the web: Transforming customer data into customer value>, John Wiley & Sons, Inc.
[34] Liu, D.、Shih, Y, < Hybrid approaches to product recommendation based on customer lifetime value and purchase preferences>, Journal of Systems and Software, vol.77, no.2, pp.181-191, 2005 
[35] Maglio, P、Bailey, J、Gruhl, D, <Steps toward a science of service systems>, Computer, vol.40, pp.71-77, 2007 
[36] McCarty, J. A.、Hastak, M, <Segmentation approaches in data-mining: A comparison of RFM, CHAID, and logistic regression>, Journal of Business Research, vol.60, no.6, pp.656-662, 2007 
[37] Miglautsch、J.R, < Thoughts on RFM scoring>. The Journal of Database Marketing, vol.8, no.1, pp.67-72, 2000. 
[38] Ng, I. C.、Maull, R.、Yip, N, .<Outcome-based contracts as a driver for systems thinking and service-dominant logic in service science: Evidence from the defence industry>, European Management Journal, vol.27, no.6, pp.377-387, 2009 
[39] Rong, J.、Vu, H. Q、Law, R.、Li, G., <A behavioral analysis of web sharers and browsers in hong kong using targeted association rule mining>, Tourism Management, vol.33, no.4, pp.731-740, 2012. 
[40] Sampson, S. E.、Froehle、C. M., <Foundations and implications of a proposed unified services theory>, Production and Operations Management, vol.15, no.2, pp.329-343, 2006. 
[41] Schijns, J、Schr&ouml;der, G. J, <Segment selection by relationship strength>, Journal of Direct Marketing, vol.10, no.3, pp.69-79, 1996
[42] Shim, B.、Choi, K.,、Suh, Y, <CRM strategies for a small-sized online shopping mall based on association rules and sequential patterns>, Expert Systems with Applications, vol.39, no.9, pp.7736-7742, 2012
[43] Spohrer, J.、Maglio, P, <Emergence of service science: Services sciences, management, engineering (SSME) as the next frontier in innovation>, Presentation at IBM Almaden Research Center, 2005 
[44] Spohrer, J.、Vargo, S. L.、Caswell, N.、Maglio, P. P., < The service system is the basic abstraction of service science>, Hawaii International Conference on System Sciences, Proceedings of the 41st Annual, pp.104-104 
[45] Tsai, C.、Chiu, C, <A purchase-based market segmentation methodology>, Expert Systems with Applications, vol.27, no.2, pp.265-276, 2004 
[46]Vargo, S. L、Lusch, R. F, <Evolving to a new dominant logic for marketing>.Journal of Marketing, vol.68, no.1, pp.1-17, 2004 
[47] Vargo, S. L.、Lusch, R. F., <From goods to service (s): Divergences and convergences of logics>, Industrial Marketing Management, vol.37, no.3, pp.254-259, 2008 
[48] Wang, Y.、Chuang, Y、Hsu, M、Keh, H., <A personalized recommender system for the cosmetic business>, Expert Systems with Applications, vol.26, no.3, pp 427-434, 2004
[49] Wu, J., & Lin, Z., <Research on customer segmentation model by clustering>, Proceedings of the 7th International Conference on Electronic Commerce, pp.316-318. 
[50] Zhao, Q.、Bhowmick, S. S., <Association rule mining: A survey>, Nanyang Technological University, Singapore, 2003
[51] Zheng, C. L.、Hao, K. R.、Ding, Y. S, <A collaborative filtering recommendation algorithm incorporated with life cycle>, Advanced Materials Research, 765, pp.630-633, 2013
[52] Rakesh Agrawal、Ramakrishnan Srikan,<Fast Algorithms for Mining Association Rules
>, Proceedings of the 20th VLDB Conference, Santiago, Chile, 1994