近幾年國內電信系統商為了爭取用戶數，針對不同客層推出不同的資費內容，不同的資費亦可能不同的身份資格、預繳資格、區域別等推出不同的優惠項目。而每項資費可搭配不同的商品。在不同條件的交叉組合下即產生了數十萬種的門號資費與商品組合。如此，通訊零售商面對如此龐大且複雜的門市資費組合及商品，無法判斷企業內部需要銷售策略、市場的需求與競爭優勢，更無法同時考量使用者的實際需求與企業利益來進行銷售。
本研究設計一混合K-means與C5.0決策樹之方法，用以建構銷售推薦法則模型。透過歷史銷售紀錄進行資料探勘技術分析，在不同條件、資費與商品的組合下，挑出收益較高及成交次數較高的門號資費組合。而後將這些優良的組合進行規則分析，產生專案資費推薦模型。讓銷售人員在銷售時能針對不同需求的客戶，提供符合需求且收益最大化的門號資費組合。

Most of existing studies on the telecom retail industry were mainly based on market segmentation or customer research. No prior study was conducted on the improvement of gross profit in the telecom retail industry. Several studies were conducted on data mining and retail sales, but data exploration was not conducted to analyze the sales information of telecom retailers. Thus, the present study will use K-mean combined with C5.0 to analyze the historical sales information of telecom retailers and establish a special tariff model that can assist salespersons. The data set will be divided into four, namely, the main data set, F-carrier data set, W-telecom data set, and T-telecom data set. The K-mean group will be used to classify the results. Rule analysis shows sales content with high gross profit and high agreement rate. The experimental results show each cluster in the four data sets, which can be used to identify rules for the combination of good tariff items in different tariff ranges. The rules for recommendation of special tariffs are established to assist salespersons.

摘要......................................................................i
Abstract.................................................................ii
誌謝.....................................................................iii
目錄......................................................................iv
表目錄....................................................................v
圖目錄...................................................................vii
第一章 緒論.............................................................1
1.1研究背景與動機.........................................................1
1.2研究問題...............................................................2
1.3研究目的...............................................................3
1.4研究流程與架構..........................................................3
第二章 文獻探討..........................................................5
2.1電信產業相關研究.........................................................5
2.2資料探勘相關研究.........................................................5
2.3 K-MEAN 分群方法........................................................6
2.4 C5.0決策樹分類方法.....................................................9
第三章 研究方法.........................................................11
3.1 研究架構.............................................................11
3.2 研究架構步驟說明.......................................................13
3.2.1資料搜集與前處理......................................................13
3.2.2分群分析............................................................13
3.2.3法則分析............................................................13
第四章 研究結果.........................................................15
4.1 資料集與前處理.......................................................15
4.2 實驗結果.............................................................19
4.2.1叢集一之銷售推薦法則集合.............................................20
4.2.2叢集二之銷售推薦法則集合.............................................36
4.2.3叢集三之銷售推薦法則集合.............................................53
4.2.4叢集四之銷售推薦法則集合.............................................60
4.2.5叢集五之銷售推薦法則集合.............................................82
第五章 結論與未來展望...................................................93
參考文獻.................................................................94
Extended Abstract.......................................................97

Black, K. (2011). Business statistics: for contemporary decision making. John Wiley & Sons.
Berry, M. J., & Linoff, G. (1997). Data mining techniques: for marketing, sales, and customer support. John Wiley & Sons, Inc..
B. Liu, W. Hsu, L.F. Mun, and H.Y. Yan (1999).“Finding Interesting Patterns Using User Expectations,” IEEE Transactions on Knowledge and Data Engineering, Vol. 11, No.6.
Chen, M. S., Han, J., & Yu, P. S. (1996). Data mining: an overview from a database perspective. IEEE Transactions on Knowledge and data Engineering, Vol. 8, No. 6, 866-883.
Cabena, P., Hadjinian, P., Stadler, R., Verhees, J., & Zanasi, A., International Business Machines Corporation (San Jose, California), & International Technical Support Organization (San Jose, California). (1997). Discovering data mining: from concept to implementation (p. 27). New Jersey: Prentice Hall PTR.
Ghani, R., & Simmons, H. (2004). Predicting the end-price of online auctions. In Proceedings of the International Workshop on Data Mining and Adaptive Modelling Methods for Economics and Management (pp. 1-11).
H.-J. Chiang, C.-C. Tseng and C.-C. Torng (2013). “A retrospective analysis of prognostic indicators in dental implant therapy using the C5.0 decision tree algorithm”, Journal of Dental Sciences, Vol. 8, No. 3, pp. 248-255.
J. MacQueen (1967). “Some methods for classification and analysis of multivariate 58 observations”, Proceedings of the fifth Berkeley symposium on mathematical statistics and probability, Vol. 1, No 14, pp. 281-297.
Moloud Abdar, Mariam Zomorodi-Moghadam, Resul Das, I-HsienTing (2017). “Performance analysis of classification algorithms on early detection of liver disease”, Expert Systems with Applications, Vol. 67, Pages 239-251.
M. Ghodousi, A. A. Alesheikh and B. Saeidian (2016). “Analyzing public participant data to evaluate citizen satisfaction and to prioritize their needs via K-means.”, FCM and ICA.Vol. 55, pp. 70-81.
P. Cabena, P. Hadjiniian, R. Stadler, J. Verhees and A. Zanasi (1997).“Discovering Data Mining From Concept to Implementation,” Prentice-Hall Inc.
Quinlan, J. R. (1986). Induction of decision trees. Machine learning, Vol. 1, No. 1, pp. 81-106.
S. Zahra, M. A. Ghazanfar, A. Khalid, M. A. Azam, U. Naeem and A. PrugeiBennett (2015). “Novel centroid selection approaches for KMeans-clustering based recommender systems”, Information Sciences, Vol. 320, pp. 156-189.
Sheikh, K. (2003). Manufacturing resource planning (MRP II): with introduction to ERP, SCM and CRM. McGraw-Hill Professional Publishing.
Siknun and Sitanggang (2016) “Web-based Classification Application for Forest Fire Data Using the Shiny Framework and the C5.0 Algorithm“, Procedia Environmental Sciences, Vol. 33, pp. 332-339.
Taylor, B. W., Bector, C. R., Bhatt, S. K., & Rosenbloom, E. S. (2015). Introduction to management science. Prentice Hall.
程信賢. (2002). 行動電話消費者購買行為及其市場區隔之研究─ 以南部地區為例. 成功大學企業管理學系碩士在職專班學位論文, 1-127.行動電話顧客流失行為探討
吳坤泉. (2002). 行動電話顧客流失行為探討. 成功大學高階管理碩士在職專班 (EMBA) 學位論文, 1-51.
許哲瑋. (2002). 資料挖掘與統計方法應用於資料庫行銷之實證研究─ 以美妝保養品業為例. 台北大學企業管理研究所碩士論文。
范國恩. (2004). 行動電話服務市場之轉換用戶市場區隔研究-以台北市地區為例行動電話服務市場之轉換用戶市場區隔研究-以台北市地區為例
高子婷(2006). 以集群分析探討結構性改變－以台灣加權股價指數為例。逢甲大學國際貿易所碩士論文。
羅巧芳, 吳信宏, 張恩啓, & 鄭易英. (2008). 應用資料探勘於戶外活動用品專賣店之顧客忠誠及價值分析. 品質學報, 15(4), 293-303.
馮秀卿(2008). 以群集分析技術探討同縣市醫學中心婦產科病患就醫特性—以台中市為例。東海大學工業工程與經營資訊研究所碩士論文。
張皇裕(2008). 運用地理資訊精進房貸風險預測。輔仁大學資訊工程研究所碩士論文.
涂永營.(2009). 應用資料探勘於顧客價值與產品關聯分析之研究－以水療業為例。國立高雄應用科技大學資訊管理系碩士在職專班碩士論文。
廖述賢與溫志皓，(2009)。資料採礦與商業智慧。台北：雙葉書廊
林良泰, & 陳乃萁. (2010). K-means 集群分析法應用於號誌定時時制時段劃分之研究. 運輸學刊, 22(3), 347-368.
歐宗殷(2010). 資料探勘為基礎之零售業銷售預測模式-以連鎖超商鮮食商品為例。國立清華大學工業工程與工程管理研究所碩士論文。
黃秉文. (2011). 運用資料採礦的技術探討金字塔客戶之流失模式-以某量販店為例
林佳青(2015). 以客服中心通話行為預測分析顧客流失率-以A公司為例。元智大學資訊管理學系碩士班碩士論文。
詹于葳(2016). 應用資料探勘建立分類反應模型於電信資費與商品組合分析之研究。國立中央大學企業管理學系碩士論文。