本研究個案現有推薦系統產生之營收占比約5%，仍有成長空間。為提升推薦績效，本研究透過個案交易資料分析，探討促銷活動對整體營收之影響，推導出以促銷商品價格優惠活動做為新的推薦因子，並將此推薦因子加入現有推薦系統中，基於推薦系統具有個人化的特性，進而形成個人化促銷商品推薦。
實際驗證後發現在具有價格優惠的因素下，針對個別消費者推薦適合的促銷商品，推薦營收占比由5%提升至6.51%，成長率30%;訂單轉換率由1.74%提升至2.15%，成長率23%。除證明價格促銷對於消費者具有刺激其完成交易的影響力之外，也證明價格促銷運用在個人化推薦系統上，具有提升推薦績效的效果。

This case study shows that the current recommendation system contributes to approximately 5% of the total revenue and that there is scope to increase this percentage. To enhance the performance of the recommendation system, this study analyzed trading data and investigated the effect of promotional activities on the overall revenue. Moreover, it identified the pricing of promotional items as a new recommendation factor and incorporated this factor into the existing recommendation system. The system is capable of customer personalization; hence, it can recommend unique products to individual customers.
The study found that with the addition of the price promotion factor, recommending appropriate promotional products to individual consumers led to an increase in the percentage of revenue resulting from recommendations ranging from 5% to 6.51% as well as an increase in the order conversion rate ranging from 1.74% to 2.15%. The findings provide evidence for the argument that price promotions stimulate the completion of transaction processes in the purchase-decision process of consumers. Furthermore, the study shows that price promotions can be applied to personalized recommendation systems for increasing the percentage of revenue resulting from such recommendations.

目錄 III
表目錄 V
圖目錄 VI
第一章 緒論 1
第一節 研究背景與動機 1
第二節 研究目的 2
第三節 論文架構 3
第二章 文獻探討 4
第一節 推薦系統定義與分類 4
第二節 電子商務個人化推薦系統 12
第三節 網路促銷模式與定義 14
第四節 網路個人化銷售 17
第三章 研究設計 21
第一節 研究方法 21
第二節 研究對象 22
第三節 研究流程 22
第四章 個案研究與分析 24
第一節 個案背景 24
第二節 個案商品推薦策略 28
第三節 個案商品促銷策略 33
第四節 個人化推薦促銷商品 37
第五節 主要發現 50
第五章 結論與建議 53
第一節 結論 53
第二節 建議 54
參考文獻 57

表目錄
==========================================
表2-1 各種推薦技術 10
表2-2 線上銷售促銷分類模式 16
表4-1 個案2013年及2014年營收及毛利額成長率 24
表4-2 個案2014/07~2014/11推薦績效 25
表4-3 每日同步至推薦系統之資料項目 29
表4-4 個案促銷商品類別及促銷條件 34
表4-5 個案2014年促銷活動成效同期比較 35
表4-6 個案2014年中元節促銷活動同期比 36
表4-7 個案2014/07~2014/11商品類別促銷營收/賣出占比 37
表4-8 個人化推薦促銷之推薦因子 40
表4-9 AB測試成效評估 44
表4-10 個人化推薦促銷商品績效 46
表4-11 個案2014/12~2015/01推薦績效 47
表4-12 個案2014/12~2015/01商品類別促銷營收/賣出占比 47
表4-13 加入促銷推薦因子前後各數據之月平均比較 49
表4-14 促銷推薦各階段說明及成效 50

圖目錄
==========================================
圖2-1 推薦系統關聯使用者和項目的途徑 7
圖2-2 推薦系統應用區分 8
圖2-3 協同過濾推薦處理程序 11
圖2-4 電子商務個人化推薦系統 13
圖2-5 模型推薦系統之系統圖 14
圖2-6 網站個人化的發展 18
圖3-1 研究流程圖 23
圖4-1 個案推薦營收同期比較（2014/06） 27
圖4-2 個案推薦營收同期比較（2014/07） 27
圖4-3 推薦系統概念 28
圖4-4 個案推薦系統資料流程 29
圖4-5 兩階段複合式推薦 30
圖4-6 推薦系統取得消費者瀏覽記錄 31
圖4-7 熱門商品推薦模型運算流程 32
圖4-8 個案推薦系統模式 32
圖4-9 個案2014/07~2014/11商品類別促銷營收/賣出占比 37
圖4-10 個人化推薦促銷商品推導流程 38
圖4-11 個人化推薦促銷商品關聯圖 40
圖4-12 AB測試系統 42
圖4-13 AB測試流程 43
圖4-14 推薦結果展示頁面 45
圖4-15 個案2014/12~2015/01商品類別促銷營收/賣出占比 48
圖4-16 個人化促銷/非個人化促銷營收占比之比較 48

一、中文部分

[1] 余力、劉魯，2004，『電子商務個性化推薦研究』，計算機集成製造系統，第10卷．第10期，1306~1313頁。 
[2] 汪軒楷，2002，『策略式資料探勘在個人化推薦上之研究』，真理大學管理科學學系碩士論文。 
[3] 徐振軒，1998，『網際網路上促銷模式之研究』，中山大學資訊管理學系碩士論文。 
[4] 梁基岩譯，1992，『行銷學要義』，曉園出版社。 
[5] 郭偉光，2014，『我國B2C電子商務個性化商品推薦服務實證研究』，價值工程，第33卷．第30期，25~27頁。 
[6] 項亮，2012，『推薦系統實踐』，人民郵電出版社。 
[7] 黃升煌，2009，『以顧客動態購買興趣樣式為基礎並考慮產品利潤之協同推薦系統』，高雄第一科技大學資訊管理學系碩士論文。 
[8] 歐仁德，2006，『結合本體論與通用個人輪廓於個人化推薦之研究』，朝陽科技大學資訊管理學系碩士論文。 
[9] 蔡松霖，2013，『電子商務推薦系統模型之初探』，東華大學企業管理學系博士論文。


二、英文部分

[1] Aaker, D. A. 1996. "Measuring Brand Equity Across Products and Markets," California Management Review (38:3), pp. 103. 
[2] Adomavicius, G., and A. Tuzhilin. 2005. "Toward the Next Generation of Recommender Systems: A Survey of the State-of-the-Art and Possible Extensions," Knowledge and Data Engineering, IEEE Transactions On (17:6), pp. 734-749. 
[3] Baeza-Yates, R., and B. Ribeiro-Neto. 1999. "Modern Information Retrieval," ACM press New York. 
[4] Balabanović, M., and Y. Shoham. 1997. "Fab: Content-Based, Collaborative Recommendation," Communications of the ACM (40:3), pp. 66-72. 
[5] Basu, C., H. Hirsh, and W. Cohen. 1998. "Recommendation as Classification: Using Social and Content-Based Information in Recommendation," pp. 714-720. 
[6] Beem, E. R., and H. J. Shaffer. 1981. "Triggers to Customer Action: Some Elements in a Theory of Promotional Inducement," Marketing Science Institute.
[7] Blackwell, R. D., P. W. Miniard, and J. F. Engel. 2001. "Consumer Behavior 9th," South-Western Thomas Learning. Mason, OH. 
[8] Blattberg, R. C., and S. A. Neslin. 1990. "Sales Promotion: Concepts, Methods, and Strategies," Prentice Hall Englewood Cliffs, NJ. 
[9] Breese, J. S., D. Heckerman, and C. Kadie. 1998. "Empirical Analysis of Predictive Algorithms for Collaborative Filtering," pp. 43-52. 
[10] Campbell, L., and W. D. Diamond. 1990. "Framing and Sales Promotions: The Characteristics of a 'Good Deal'," Journal of Consumer Marketing (7:4), pp. 25-31. 
[11] Chandon, P., B. Wansink, and G. Laurent. 2000. "A Benefit Congruency Framework of Sales Promotion Effectiveness," Journal of Marketing (64:4), pp. 65-81. 
[12] Claypool, M., A. Gokhale, T. Miranda, P. Murnikov, D. Netes, and M. Sartin. 1999. "Combining Content-Based and Collaborative Filters in an Online Newspaper," In Proceedings of ACM SIGIR workshop on recommender systems. 
[13] Dean, R. 1998. "Personalizing Your Web Site," Retrieved June. 
[14] Goldberg, D., D. Nichols, B. M. Oki, and D. Terry. 1992. "Using Collaborative Filtering to Weave an Information Tapestry," Communications of the ACM (35:12), pp. 61-70. 
[15] Hanani, U., B. Shapira, and P. Shoval. 2001. "Information Filtering: Overview of Issues, Research and Systems," User Modeling and User-Adapted Interaction (11:3), pp. 203-259. 
[16] Kilfoil, M., A. Ghorbani, W. Xing, Z. Lei, J. Lu, J. Zhang, and X. Xu. 2003. "Toward an Adaptive Web: The State of the Art and Science," pp. 108-119. 
[17] Lawrence, R. D., G. S. Almasi, V. Kotlyar, M. Viveros, and S. S. Duri. 2001. "Personalization of Supermarket Product Recommendations," Data Mining and Knowledge Discovery, (5:1-2), pp.11-32. 
[18] Linden, G., B. Smith, and J. York. 2003. "Amazon. Com Recommendations: Item-to-Item Collaborative Filtering," Internet Computing, IEEE (7:1), pp. 76-80. 
[19] Pazzani, M. J. 1999. "A Framework for Collaborative, Content-Based and Demographic Filtering," Artificial Intelligence Review (13:5-6), pp. 393-408. 
[20] Quelch, J. A. 1989. "Sales Promotion Management," Prentice-Hall, Englewood Cliffs, NJ. 
[21] Raghubir, P., and K. Corfman. 1999. "When do Price Promotions Affect Pretrial Brand Evaluations?" Journal of Marketing Research pp. 211-222. 
[22] Resnick, P., and H. R. Varian. 1997. "Recommender Systems," Communications of the ACM (40:3), pp. 56-58. 
[23] Ricci, F. 2002. "Travel Recommender Systems," IEEE Intelligent Systems (17:6), pp. 55-57. 
[24] Sarwar, B., G. Karypis, J. Konstan, and J. Riedl. 2000. "Analysis of Recommendation Algorithms for E-Commerce," pp. 158-167. 
[25] Schafer, J. B., J. A. Konstan, and J. Riedl. 2001. "E-Commerce Recommendation Applications," Applications of Data Mining to Electronic Commerce, Anonymous Springer, pp. 115-153. 
[26] Schafer, J. B., J. Konstan, and J. Riedl. 1999. "Recommender Systems in E-Commerce," pp. 158-166. 
[27] Surprenant, C. F., and M. R. Solomon. 1987. "Predictability and Personalization in the Service Encounter," The Journal of Marketing pp. 86-96. 
[28] Terveen, L., and W. Hill. 2001. "Beyond Recommender Systems: Helping People Help each Other," HCI in the New Millennium, 1, pp. 487-509. 
[29] Vig, J., S. Sen, and J. Riedl. 2009. "Tagsplanations: Explaining Recommendations using Tags," pp. 47-56. 
[30] Yin, R. 1994. "Case Study Research: Design and Methods," Beverly Hills.