電子商務自1990年代興起以來，經歷了多個階段的轉變。到了2020年代，疫情推動全球零售業向電子商務轉型，大量新用戶湧入電商平台。此時，平台開始廣泛應用人工智慧和大數據技術，提高個性化推薦系統和顧客服務水平。此外，少子化趨勢提升了寵物用品的需求，要求電商平台提供更多元化和個性化的服務。在競爭激烈的市場中，電商平台必須創新策略來吸引和留住顧客。面對既有顧客流失和冷啟動問題，電商平台需要迅速分析交易數據並生成精準的推薦。這樣可以更好地了解顧客行為及商品特徵，並設計客製化的行銷活動，有效提升銷售效果。
本研究運用非監督式學習方法，對某寵物電商銷售交易紀錄進行分析，使用非負矩陣分解（Non-Negative Matrix Factorization, NMF）演算法，深入分析顧客購買行為，提取特徵並進行客戶分群。此方法，我們可以識別出不用偏好的顧客分群，擬定策略主題，目的是提升銷售業績和顧客滿意度，並且能夠幫助企業精準定位市場。

Since its emergence in the 1990s, e-commerce has undergone multiple stages of transformation. By the 2020s, the pandemic has driven the global retail industry to transition towards e-commerce, bringing a large influx of new users to online platforms. At this time, platforms began to widely apply artificial intelligence and big data technologies to enhance personalized recommendation systems and customer service levels. Additionally, the trend of declining birth rates has increased the demand for pet supplies, requiring e-commerce platforms to provide more diverse and personalized services. In a highly competitive market, e-commerce platforms must innovate strategies to attract and retain customers. Faced with existing customer churn and cold start problems, e-commerce platforms need to quickly analyze transaction data and generate precise recommendations. This approach can better understand customer behavior and product characteristics, allowing for the design of customized marketing campaigns that effectively boost sales performance.

This study employs unsupervised learning methods to analyze the sales transaction records of a pet e-commerce platform, using the Non-Negative Matrix Factorization (NMF) algorithm to deeply analyze customer purchasing behavior, extract features, and perform customer segmentation. Through this method, we can identify customer segments with different preferences, formulate strategic themes, with the aim of enhancing sales performance and customer satisfaction, and helping businesses accurately target the market.

論文審定書 i
誌謝 ii
摘要 iii
Abstract iv
目錄 v
圖次 vii
表次 viii
第壹章 緒論 1
第一節 研究背景 1
第二節 研究動機 1
第三節 研究目的 2
第貳章 文獻探討 3
第一節 推薦系統(RECOMMENDATION SYSTEM) 3
第二節 矩陣分解(MATRIX FACTORIZATION) 6
第三節 非負矩陣分解（NMF） 8
第四節 跨類別和交叉類別效應(CROSS-CATEGORY EFFECT) 9
第五節 捆綁策略 (BUNDLING STRATEGY) 10
第參章 研究方法 11
第一節 數據集說明 11
第二節 研究流程 11
第三節 評估模型準則 14
第肆章 實證與分析 15
第一節 資料整理描述 15
第二節 資料合併 16
第三節 評分矩陣 17
第四節 實證結果 18
第五節 NMF策略應用 25
第伍章 研究結論與建議 33
第一節 研究結論 33
第二節 限制與建議 33
第陸章 參考文獻 34

Bandyopadhyay, S. (2009). A Dynamic Model of Cross-Category Competition: Theory, Tests and Applications. Journal of Retailing, 85(4), 468–479. https://doi.org/10.1016/j.jretai.2009.05.001
Beladev, M., Rokach, L., & Shapira, B. (2016). Recommender systems for product bundling. Knowledge-Based Systems, 111, 193–206. https://doi.org/10.1016/j.knosys.2016.08.013
Brunet, J.-P., Tamayo, P., Golub, T. R., & Mesirov, J. P. (2004). Metagenes and molecular pattern discovery using matrix factorization. Proceedings of the National Academy of Sciences, 101(12), 4164–4169. https://doi.org/10.1073/pnas.0308531101
B.Thorat, P., M. Goudar, R., & Barve, S. (2015). Survey on Collaborative Filtering, Content-based Filtering and Hybrid Recommendation System. International Journal of Computer Applications, 110(4), 31–36. https://doi.org/10.5120/19308-0760
Cai, D., He, X., Wu, X., & Han, J. (2008). Non-negative Matrix Factorization on Manifold. 2008 Eighth IEEE International Conference on Data Mining, 63–72. https://doi.org/10.1109/ICDM.2008.57
Duvvuri, S. D., Ansari, A., & Gupta, S. (2007). Consumers’ Price Sensitivities Across Complementary Categories. Management Science, 53(12), 1933–1945. https://doi.org/10.1287/mnsc.1070.0744
Gan 等。—2021—Non-negative Matrix Factorization A Survey. (n.d.).
George, T., & Merugu, S. (2005). A Scalable Collaborative Filtering Framework Based on Co-Clustering. Fifth IEEE International Conference on Data Mining (ICDM’05), 625–628. https://doi.org/10.1109/ICDM.2005.14
Goldberg, D., Nichols, D., Oki, B. M., & Terry, D. (1992). Using collaborative filtering to weave an information tapestry. Communications of the ACM, 35(12), 61–70. https://doi.org/10.1145/138859.138867
Goldberg, K., Roeder, T., Gupta, D., & Perkins, C. (n.d.). Eigentaste: A Constant Time Collaborative Filtering Algorithm.
González-Benito, Ó., Martínez-Ruiz, M. P., & Mollá-Descals, A. (2010). Retail pricing decisions and product category competitive structure. Decision Support Systems, 49(1), 110–119. https://doi.org/10.1016/j.dss.2010.01.009
Gunawardana, A., & Shani, G. (n.d.). A Survey of Accuracy Evaluation Metrics of Recommendation Tasks.
Gunawardana and Shani—A Survey of Accuracy Evaluation Metrics of Recomme. (n.d.).
Hamidzadeh, J., & Kelidari, M. (2022). Robust Feature Selection by Filled Function and Fisher Score. https://doi.org/10.21203/rs.3.rs-1102788/v1
Jeuland, A. (1984). Comments on “Gaussian Demand and Commodity Bundling.” The Journal of Business, 57(1,), S231–S234. http://www.jstor.org/stable/2352938
Jiang, Y., Shang, J., Liu, Y., & May, J. (2015). Redesigning promotion strategy for e-commerce competitiveness through pricing and recommendation. International Journal of Production Economics, 167, 257–270. https://doi.org/10.1016/j.ijpe.2015.02.028
Koren, Y. (n.d.). Factorization Meets the Neighborhood: A Multifaceted Collaborative Filtering Model.
Lee, D. D., & Seung, H. S. (1999). Learning the parts of objects by non-negative matrix factorization. Nature, 401(6755), 788–791. https://doi.org/10.1038/44565
Li, M., & Wang, L. (2019). A Survey on Personalized News Recommendation Technology. IEEE Access, 7, 145861–145879. https://doi.org/10.1109/ACCESS.2019.2944927
Melville, P., Mooney, R. J., & Nagarajan, R. (n.d.). Content-Boosted Collaborative Filtering for Improved Recommendations.
Mnih, A., & Salakhutdinov, R. R. (n.d.). Probabilistic Matrix Factorization.
Niraj, R., Padmanabhan, V., & Seetharaman, P. B. (2008). A Cross-Category Model of Households’ Incidence and Quantity Decisions. Marketing Science, 27(2), 225–235. http://www.jstor.org/stable/40057098
Raghuwanshi, S. K., & Pateriya, R. K. (2019). Recommendation Systems: Techniques, Challenges, Application, and Evaluation. In J. C. Bansal, K. N. Das, A. Nagar, K. Deep, & A. K. Ojha (Eds.), Soft Computing for Problem Solving (Vol. 817, pp. 151–164). Springer Singapore. https://doi.org/10.1007/978-981-13-1595-4_12
Resnick, P., Iacovou, N., Suchak, M., Bergstrom, P., & Riedl, J. (1994). GroupLens: An open architecture for collaborative filtering of netnews. Proceedings of the 1994 ACM Conference on Computer Supported Cooperative Work - CSCW ’94, 175–186. https://doi.org/10.1145/192844.192905
Sarwar, B., Karypis, G., Konstan, J., & Riedl, J. (2000a). Analysis of recommendation algorithms for e-commerce. Proceedings of the 2nd ACM Conference on Electronic Commerce, 158–167. https://doi.org/10.1145/352871.352887
Sarwar, B., Karypis, G., Konstan, J., & Riedl, J. (2000b). Application of Dimensionality Reduction in Recommender System—A Case Study: Defense Technical Information Center. https://doi.org/10.21236/ADA439541
Sarwar, B., Karypis, G., Konstan, J., & Riedl, J. (2001). Item-based collaborative filtering recommendation algorithms. Proceedings of the 10th International Conference on World Wide Web, 285–295. https://doi.org/10.1145/371920.372071
Smaragdis, P., & Brown, J. C. (2003). Non-negative matrix factorization for polyphonic music transcription. 2003 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (IEEE Cat. No.03TH8684), 177–180. https://doi.org/10.1109/ASPAA.2003.1285860
Stremersch, S., & Tellis, G. J. (2002). Strategic Bundling of Products and Prices: A New Synthesis for Marketing. Journal of Marketing, 66(1), 55–72. https://doi.org/10.1509/jmkg.66.1.55.18455
Su, X., & Khoshgoftaar, T. M. (2009). A Survey of Collaborative Filtering Techniques. Advances in Artificial Intelligence, 2009, 1–19. https://doi.org/10.1155/2009/421425
Vu Ngoc, T., & Tran Thi, H. (2021, August 2). Techniques, benefits, and challenges of recommendation system in e-commerce: A literature review. Proceedings of the International Conference on Industrial Engineering and Operations Management. 4th European International Conference on Industrial Engineering and Operations Management, Rome, Italy. https://doi.org/10.46254/EU04.20210436
Xu, W., Liu, X., & Gong, Y. (2008). Document Clustering Based On Non-negative Matrix Factorization.
Yulianto 等。—2021—The Stimulus Of Impulse Buying Behavior On E-Comme. (n.d.).
Zhu, T., Harrington, P., Li, J., & Tang, L. (2014). Bundle recommendation in ecommerce. Proceedings of the 37th International ACM SIGIR Conference on Research & Development in Information Retrieval, 657–666. https://doi.org/10.1145/2600428.2609603
朱欣容—2021—電商造節行銷對消費者衝動購買行為影響研究—以蝦皮購物為例, (n.d.).