學術產出-Theses
Article View/Open
Publication Export
-
題名 基於內隱資料之協同過濾推薦系統研究與實作
Research and application for collaborative filtering recommendation system using implicit datasets作者 張遠耀
Chang, Yuan Yao貢獻者 洪叔民
Horng, Shwu Min
張遠耀
Chang, Yuan Yao關鍵詞 推薦系統
內隱資料
協同過濾
潛在因子
矩陣分解日期 2017 上傳時間 31-Jul-2017 11:35:33 (UTC+8) 摘要 近年來電子商務蓬勃發展，嚴重侵蝕實體通路業績，因此線下服務提供者更應善用資料科學技術，找出顧客未被滿足之需求，進而提供優質服務，其中脫穎而出的關鍵非推薦系統莫屬。本研究以運用計算產品相似程度的「項目導向協同過濾」和計算使用者與商品蘊含特徵的「潛在因子」兩大類「協同過濾」推薦方法為核心，藉由實體零售通路累積的顧客消費紀錄，驗證「協同過濾」方法較傳統熱門商品推薦機制更符合消費者偏好，且「協同過濾」方法能達到完全個人化推薦之目標。本研究使用的實體零售通路消費紀錄源於顧客真實購物行為，收集成本低，且數據量龐大，然而此類資料無法直接傳達顧客對於商品的喜好與滿足程度，因此被稱之為「內隱資料」，針對內隱資料處理上，本研究選擇以消費次數取代金額，提出短期重複行為計算閾值概念，以時間修正權重處理可能的偏好轉變與習慣性消費。模型評估方面，透過強調推薦順序的「平均排名百分比」作為指標，利用傳統熱門商品推薦為基準，比較「項目導向協同過濾」和「潛在因子」兩大類「協同過濾」方法推薦品質的優劣，本研究顯示兩大類「協同過濾」方法達到的推薦品質皆優於熱門商品推薦，且前者遞交的推薦清單為完全個人化，運用本研究發展的推薦系統，將其導入與應用，讓線下服務提供者在與每位顧客接觸的關鍵時刻，能在洞悉對方需求的利基上，提供令顧客滿意的商品與服務，創造獨特且難以模仿的競爭優勢。 參考文獻 [1] How retailers can keep up with consumers. Retrieved October 2013. from: http://www.mckinsey.com/industries/retail/our-insights/how-retailers-can-keep-up-with-consumers[2] Netflix Prize. from: http://www.netflixprize.com/community/forum.html[3] YouTube statistics. from: https://www.youtube.com/yt/press/statistics.html[4] Davidson, J., Liebald, B., Liu, J., Nandy, P., Van Vleet, T., Gargi, U., Gupta, S., He, Y., Lambert, M., Livingston, B., & Sampath, D. (2010). The YouTube video recommendation system. In Proceedings of the fourth ACM conference on Recommender systems. 293–296.[5] Facebook newsroom, company info, statistics. from: https://www.youtube.com/yt/press/zh-TW/statistics[6] Recommending items to more than a billion people. Retrieved June 3 2015. from: https://code.facebook.com/posts/861999383875667/recommending-items-to-morm-than-a-billion-people/[7] 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.[8] Konstan, J. A., Miller, B. N., Maltz, D., Herlocker, J. L., Gordon, L. R., & Riedl, J. (1997). GroupLens: applying collaborative filtering to Usenet news. Communications of the ACM. 40(3). 77-87.[9] Harper, F. M., & Konstan, J. A. (2016). The MovieLens datasets: history and context. ACM Transactions on Interactive Intelligent Systems (TiiS). 5(4). Article No.: 19. 1-20.[10] Linden, G., Smith, B., & York, J. (2003). Amazon.com recommendations: Item-to-item collaborative filtering. IEEE Internet computing. 7(1). 76-80.[11] Covington, P., Adams, J., & Sargin, E. (2016). Deep neural networks for youtube recommendations. In Proceedings of the 10th ACM Conference on Recommender Systems. 191-198.[12] Bell, R. M., & Koren, Y. (2007). Lessons from the Netflix prize challenge. ACM Sigkdd Explorations Newsletter. 9(2). 75-79.[13] Listen to Pandora, and it listens back. Retrieved January 4 2014. from: https://www.nytimes.com/2014/01/05/technology/pandora-mines-users-data-to-better-target-ads.html?_r=0[14] Ali, K., & Van Stam, W. (2004). TiVo: making show recommendations using a distributed collaborative filtering architecture. In Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining. 394-401.[15] Pazzani, M. J. (1999). A framework for collaborative, content-based and demographic filtering. Artificial Intelligence Review. 13(5-6). 393-408.[16] Pazzani, M. J., & Billsus, D. (2007). Content-based recommendation systems. The adaptive web. 325-341.[17] Ramos, J. (2003). Using tf-idf to determine word relevance in document queries. In Proceedings of the first instructional conference on machine learning.[18] Tata, S., & Patel, J. M. (2007). Estimating the selectivity of TF-IDF based cosine similarity predicates. ACM Sigmod Record. 36(2). 7-12.[19] Huang, A. (2008). Similarity measures for text document clustering. In Proceedings of the sixth New Zealand computer science research student conference. 49-56.[20] Herlocker, J. L., Konstan, J. A., Terveen, L. G., & Riedl, J. T. (2004). Evaluating collaborative filtering recommender systems. ACM Transactions on Information Systems (TOIS). 22(1). 5-53.[21] Papagelis, M., & Plexousakis, D. (2005). Qualitative analysis of user-based and item-based prediction algorithms for recommendation agents. Engineering Applications of Artificial Intelligence. 18(7). 781-789.[22] Adomavicius, G., & Tuzhilin, A. (2005). Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. IEEE transactions on knowledge and data engineering. 17(6). 734-749.[23] Wang, J., De Vries, A. P., & Reinders, M. J. (2006). Unifying user-based and item-based collaborative filtering approaches by similarity fusion. In Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval. 501-508.[24] Sarwar, B., Karypis, G., Konstan, J., & Riedl, J. (2001). Item-based collaborative filtering recommendation algorithms. In Proceedings of the 10th international conference on World Wide Web. 285-295.[25] Yildirim, H., & Krishnamoorthy, M. S. (2008). A random walk method for alleviating the sparsity problem in collaborative filtering. In Proceedings of the 2008 ACM conference on Recommender systems. 131-138.[26] Koren, Y., Bell, R., & Volinsky, C. (2009). Matrix factorization techniques for recommender systems. Computer. 42(8). 30-37.[27] Sarwar, B., Karypis, G., Konstan, J., & Riedl, J. (2000). Application of dimensionality reduction in recommender system-a case study. Minnesota Univ Minneapolis Dept of Computer Science.[28] Paterek, A. (2007). Improving regularized singular value decomposition for collaborative filtering. In Proceedings of KDD cup and workshop. Vol. 2007. 5-8.[29] Netflix Update: Try This at Home. Retrieved December 2006. from: http://sifter.org/~simon/journal/20061211.html[30] Rendle, S., Freudenthaler, C., Gantner, Z., & Schmidt-Thieme, L. (2009). BPR: Bayesian personalized ranking from implicit feedback. In Proceedings of the twenty-fifth conference on uncertainty in artificial intelligence. 452-461.[31] Bennett, J., & Lanning, S. (2007). The Netflix Prize. In Proceedings of KDD cup and workshop. Vol. 2007. 3-6.[32] Hu, Y., Koren, Y., & Volinsky, C. (2008). Collaborative filtering for implicit feedback datasets. In Data Mining, 2008. ICDM`08. Eighth IEEE International Conference. 263-272.[33] Surprise (Python scikit for recommender systems), Similarities Module Introduction. from: http://surprise.readthedocs.io/en/latest/similarities.html[34] Koren, Y. (2010). Factor in the neighbors: scalable and accurate collaborative filtering. ACM Transactions on Knowledge Discovery from Data. 4(1). Article No.: 1. 1-24.[35] Surprise (Python scikit for recommender systems), Matrix Factorization-based algorithms. from: http://surprise.readthedocs.io/en/latest/matrix_factorization.html[36] Sarwar, B., Karypis, G., Konstan, J., & Riedl, J. (2000). Analysis of recommendation algorithms for e-commerce. In Proceedings of the 2nd ACM conference on Electronic commerce. 158-167.[37] What do Recommender Systems experts think of the "Estimating the causal impact of recommendation systems from observational data" paper ? Answer by Xavier Amatriain. from: https://www.quora.com/What-do-Recommender-Systems-experts-think-of-the-Estimating-the-causal-impact-of-recommendation-systems-from-observational-data-paper[38] Baltrunas, L., & Amatriain, X. (2009). Towards time-dependant recommendation based on implicit feedback. In Workshop on context-aware recommender systems (CARS’09).[39] Gomez-Uribe, C. A., & Hunt, N. (2016). The netflix recommender system: Algorithms, business value, and innovation. ACM Transactions on Management Information Systems (TMIS). 6(4). Article No.: 13. 1-19. 描述 碩士
國立政治大學
企業管理研究所(MBA學位學程)
104363050資料來源 http://thesis.lib.nccu.edu.tw/record/#G1043630501 資料類型 thesis dc.contributor.advisor 洪叔民 zh_TW dc.contributor.advisor Horng, Shwu Min en_US dc.contributor.author (Authors) 張遠耀 zh_TW dc.contributor.author (Authors) Chang, Yuan Yao en_US dc.creator (作者) 張遠耀 zh_TW dc.creator (作者) Chang, Yuan Yao en_US dc.date (日期) 2017 en_US dc.date.accessioned 31-Jul-2017 11:35:33 (UTC+8) - dc.date.available 31-Jul-2017 11:35:33 (UTC+8) - dc.date.issued (上傳時間) 31-Jul-2017 11:35:33 (UTC+8) - dc.identifier (Other Identifiers) G1043630501 en_US dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/111590 - dc.description (描述) 碩士 zh_TW dc.description (描述) 國立政治大學 zh_TW dc.description (描述) 企業管理研究所(MBA學位學程) zh_TW dc.description (描述) 104363050 zh_TW dc.description.abstract (摘要) 近年來電子商務蓬勃發展，嚴重侵蝕實體通路業績，因此線下服務提供者更應善用資料科學技術，找出顧客未被滿足之需求，進而提供優質服務，其中脫穎而出的關鍵非推薦系統莫屬。本研究以運用計算產品相似程度的「項目導向協同過濾」和計算使用者與商品蘊含特徵的「潛在因子」兩大類「協同過濾」推薦方法為核心，藉由實體零售通路累積的顧客消費紀錄，驗證「協同過濾」方法較傳統熱門商品推薦機制更符合消費者偏好，且「協同過濾」方法能達到完全個人化推薦之目標。本研究使用的實體零售通路消費紀錄源於顧客真實購物行為，收集成本低，且數據量龐大，然而此類資料無法直接傳達顧客對於商品的喜好與滿足程度，因此被稱之為「內隱資料」，針對內隱資料處理上，本研究選擇以消費次數取代金額，提出短期重複行為計算閾值概念，以時間修正權重處理可能的偏好轉變與習慣性消費。模型評估方面，透過強調推薦順序的「平均排名百分比」作為指標，利用傳統熱門商品推薦為基準，比較「項目導向協同過濾」和「潛在因子」兩大類「協同過濾」方法推薦品質的優劣，本研究顯示兩大類「協同過濾」方法達到的推薦品質皆優於熱門商品推薦，且前者遞交的推薦清單為完全個人化，運用本研究發展的推薦系統，將其導入與應用，讓線下服務提供者在與每位顧客接觸的關鍵時刻，能在洞悉對方需求的利基上，提供令顧客滿意的商品與服務，創造獨特且難以模仿的競爭優勢。 zh_TW dc.description.tableofcontents 第一章 緒論 1第一節 研究背景 1第二節 研究動機與目的 3第三節 研究架構 4第二章 文獻探討 5第一節 內容導向推薦系統 5第二節 使用者導向協同過濾推薦系統 10第三節 項目導向協同過濾推薦系統 13第四節 模型導向協同過濾推薦系統 17第三章 研究方法 21第一節 研究步驟 21第二節 資料抽樣與切割 24第三節 資料處理 24第四節 指標訂定 27第五節 訓練模型參數與潛在因子 28第六節 測試模型信度 32第四章 研究分析與結果 33第一節 資料抽樣 33第二節 資料處理 40第三節 訓練模型參數與潛在因子 41第四節 測試模型信度 53第五章 結論與未來研究建議 58第一節 結論 58第二節 研究貢獻 61第三節 研究限制與未來研究建議 61參考文獻 64 zh_TW dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G1043630501 en_US dc.subject (關鍵詞) 推薦系統 zh_TW dc.subject (關鍵詞) 內隱資料 zh_TW dc.subject (關鍵詞) 協同過濾 zh_TW dc.subject (關鍵詞) 潛在因子 zh_TW dc.subject (關鍵詞) 矩陣分解 zh_TW dc.title (題名) 基於內隱資料之協同過濾推薦系統研究與實作 zh_TW dc.title (題名) Research and application for collaborative filtering recommendation system using implicit datasets en_US dc.type (資料類型) thesis en_US dc.relation.reference (參考文獻) [1] How retailers can keep up with consumers. Retrieved October 2013. from: http://www.mckinsey.com/industries/retail/our-insights/how-retailers-can-keep-up-with-consumers[2] Netflix Prize. from: http://www.netflixprize.com/community/forum.html[3] YouTube statistics. from: https://www.youtube.com/yt/press/statistics.html[4] Davidson, J., Liebald, B., Liu, J., Nandy, P., Van Vleet, T., Gargi, U., Gupta, S., He, Y., Lambert, M., Livingston, B., & Sampath, D. (2010). The YouTube video recommendation system. In Proceedings of the fourth ACM conference on Recommender systems. 293–296.[5] Facebook newsroom, company info, statistics. from: https://www.youtube.com/yt/press/zh-TW/statistics[6] Recommending items to more than a billion people. Retrieved June 3 2015. from: https://code.facebook.com/posts/861999383875667/recommending-items-to-morm-than-a-billion-people/[7] 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.[8] Konstan, J. A., Miller, B. N., Maltz, D., Herlocker, J. L., Gordon, L. R., & Riedl, J. (1997). GroupLens: applying collaborative filtering to Usenet news. Communications of the ACM. 40(3). 77-87.[9] Harper, F. M., & Konstan, J. A. (2016). The MovieLens datasets: history and context. ACM Transactions on Interactive Intelligent Systems (TiiS). 5(4). Article No.: 19. 1-20.[10] Linden, G., Smith, B., & York, J. (2003). Amazon.com recommendations: Item-to-item collaborative filtering. IEEE Internet computing. 7(1). 76-80.[11] Covington, P., Adams, J., & Sargin, E. (2016). Deep neural networks for youtube recommendations. In Proceedings of the 10th ACM Conference on Recommender Systems. 191-198.[12] Bell, R. M., & Koren, Y. (2007). Lessons from the Netflix prize challenge. ACM Sigkdd Explorations Newsletter. 9(2). 75-79.[13] Listen to Pandora, and it listens back. Retrieved January 4 2014. from: https://www.nytimes.com/2014/01/05/technology/pandora-mines-users-data-to-better-target-ads.html?_r=0[14] Ali, K., & Van Stam, W. (2004). TiVo: making show recommendations using a distributed collaborative filtering architecture. In Proceedings of the tenth ACM SIGKDD international conference on Knowledge discovery and data mining. 394-401.[15] Pazzani, M. J. (1999). A framework for collaborative, content-based and demographic filtering. Artificial Intelligence Review. 13(5-6). 393-408.[16] Pazzani, M. J., & Billsus, D. (2007). Content-based recommendation systems. The adaptive web. 325-341.[17] Ramos, J. (2003). Using tf-idf to determine word relevance in document queries. In Proceedings of the first instructional conference on machine learning.[18] Tata, S., & Patel, J. M. (2007). Estimating the selectivity of TF-IDF based cosine similarity predicates. ACM Sigmod Record. 36(2). 7-12.[19] Huang, A. (2008). Similarity measures for text document clustering. In Proceedings of the sixth New Zealand computer science research student conference. 49-56.[20] Herlocker, J. L., Konstan, J. A., Terveen, L. G., & Riedl, J. T. (2004). Evaluating collaborative filtering recommender systems. ACM Transactions on Information Systems (TOIS). 22(1). 5-53.[21] Papagelis, M., & Plexousakis, D. (2005). Qualitative analysis of user-based and item-based prediction algorithms for recommendation agents. Engineering Applications of Artificial Intelligence. 18(7). 781-789.[22] Adomavicius, G., & Tuzhilin, A. (2005). Toward the next generation of recommender systems: A survey of the state-of-the-art and possible extensions. IEEE transactions on knowledge and data engineering. 17(6). 734-749.[23] Wang, J., De Vries, A. P., & Reinders, M. J. (2006). Unifying user-based and item-based collaborative filtering approaches by similarity fusion. In Proceedings of the 29th annual international ACM SIGIR conference on Research and development in information retrieval. 501-508.[24] Sarwar, B., Karypis, G., Konstan, J., & Riedl, J. (2001). Item-based collaborative filtering recommendation algorithms. In Proceedings of the 10th international conference on World Wide Web. 285-295.[25] Yildirim, H., & Krishnamoorthy, M. S. (2008). A random walk method for alleviating the sparsity problem in collaborative filtering. In Proceedings of the 2008 ACM conference on Recommender systems. 131-138.[26] Koren, Y., Bell, R., & Volinsky, C. (2009). Matrix factorization techniques for recommender systems. Computer. 42(8). 30-37.[27] Sarwar, B., Karypis, G., Konstan, J., & Riedl, J. (2000). Application of dimensionality reduction in recommender system-a case study. Minnesota Univ Minneapolis Dept of Computer Science.[28] Paterek, A. (2007). Improving regularized singular value decomposition for collaborative filtering. In Proceedings of KDD cup and workshop. Vol. 2007. 5-8.[29] Netflix Update: Try This at Home. Retrieved December 2006. from: http://sifter.org/~simon/journal/20061211.html[30] Rendle, S., Freudenthaler, C., Gantner, Z., & Schmidt-Thieme, L. (2009). BPR: Bayesian personalized ranking from implicit feedback. In Proceedings of the twenty-fifth conference on uncertainty in artificial intelligence. 452-461.[31] Bennett, J., & Lanning, S. (2007). The Netflix Prize. In Proceedings of KDD cup and workshop. Vol. 2007. 3-6.[32] Hu, Y., Koren, Y., & Volinsky, C. (2008). Collaborative filtering for implicit feedback datasets. In Data Mining, 2008. ICDM`08. Eighth IEEE International Conference. 263-272.[33] Surprise (Python scikit for recommender systems), Similarities Module Introduction. from: http://surprise.readthedocs.io/en/latest/similarities.html[34] Koren, Y. (2010). Factor in the neighbors: scalable and accurate collaborative filtering. ACM Transactions on Knowledge Discovery from Data. 4(1). Article No.: 1. 1-24.[35] Surprise (Python scikit for recommender systems), Matrix Factorization-based algorithms. from: http://surprise.readthedocs.io/en/latest/matrix_factorization.html[36] Sarwar, B., Karypis, G., Konstan, J., & Riedl, J. (2000). Analysis of recommendation algorithms for e-commerce. In Proceedings of the 2nd ACM conference on Electronic commerce. 158-167.[37] What do Recommender Systems experts think of the "Estimating the causal impact of recommendation systems from observational data" paper ? Answer by Xavier Amatriain. from: https://www.quora.com/What-do-Recommender-Systems-experts-think-of-the-Estimating-the-causal-impact-of-recommendation-systems-from-observational-data-paper[38] Baltrunas, L., & Amatriain, X. (2009). Towards time-dependant recommendation based on implicit feedback. In Workshop on context-aware recommender systems (CARS’09).[39] Gomez-Uribe, C. A., & Hunt, N. (2016). The netflix recommender system: Algorithms, business value, and innovation. ACM Transactions on Management Information Systems (TMIS). 6(4). Article No.: 13. 1-19. zh_TW
