淡江大學覺生紀念圖書館 (TKU Library)

系統識別號 U0002-1407201115380000
中文論文名稱 推薦系統的架構與實作
英文論文名稱 The Framework of Recommender System and Implementation
校院名稱 淡江大學
系所名稱(中) 資訊工程學系碩士班
系所名稱(英) Department of Computer Science and Information Engineering
學年度 99
學期 2
出版年 100
研究生中文姓名 紀政宏
研究生英文姓名 Zheng-Hong Chi
學號 698410486
學位類別 碩士
語文別 中文
第二語文別 英文
口試日期 2011-06-19
論文頁數 97頁
口試委員 指導教授-蔣定安
中文關鍵字 推薦系統  以內容為導向推薦系統  協同過濾推薦系統  混合式推薦系統 
英文關鍵字 Recommender System  Content-based Recommender System  Collaborative Filtering Recommender System  Hybrid Recommender System 
學科別分類 學科別應用科學資訊工程
中文摘要 隨著網路科技的快速崛起,使得資訊發展所帶來的便利在生活上無所不再,而資料成長速度更是一日千里,若想在浩瀚的資料海中,尋找實際有用的資訊則相對少量,正是企業與學者主要關注的議題。為了增加企業的利益,業者必須充分蒐集與客戶相關的資訊,來經營與客戶之間的關係,以資料探勘技術來了解客戶喜好的變化,甚至利用機器學習來發展與客戶互動的智慧型商業平台,而近年來使用推薦技術應用在客戶與產品之間的行銷與決策。以電子商務而言,用於推薦分析主要是根據客戶的評價資料與交易資料,在推薦領域上,評價資料就是客戶直接給產品評價的顯性評比,而交易資料則像是客戶在網路上購買或瀏覽商品時所遺留下來的瀏覽率與購買頻率,稱為隱性評比。而本論文希望可以提出一個協同過濾的推薦架構,能應用在評價資料與交易資料上的推薦,透過客戶資料在推薦架構的應用能用在教學研究,以簡單易學的架構與流程,透過實例運算與實際資料集的測試讓初學者能快速產生連結;除此之外,本架構還可用在資料測試並讓用戶可將推薦結果與其他推薦系統作比較,讓用戶評估並選擇最佳的推薦效果。
英文摘要 Due to the rapid development of Internet, it brings humans not only more convenient in life but also makes data growth up rapidly. People face with the amount of information available and expect to use it efficiently. In order to increase the benefit, businessman must fully collect information related to customer and manage customer relationship. Recommender system has been applied for cross-selling or increasing profit between customers and products in recent years. It has been become popular for making useful recommendation to online e-commerce sites. In this paper, we mainly use the rating data or transaction data applied in recommender system. The rating data from item rated directly by customers is called explicit rating. Also, the transaction data, such as web browsing clicks, purchased records and so on, is called implicit rating. We expect to provide a framework of recommender system that employs collaborative filtering to derive recommendations. The framework can be used for teaching and research. Moreover, the process can offer a practical computation instances and dataset for freshman to learn and map easily. In this framework users can utilize data for measuring, or find out proper recommendation results through comparing with other techniques.
論文目次 第1章 緒論 1
1.1 研究動機與目的 1
1.2 研究架構 4
第2章 文獻探討 5
2.1 以內容為基礎的推薦系統 6
2.2 協同過濾推薦系統 15
2.3 混合式推薦系統 29
2.4 比較以內容為導向的推薦與協同過濾推薦 33
第3章 研究方法 37
3.1 基本架構 38
第4章 研究探討 46
4.1 討論顯性評價的使用 47
4.1.1 預測與精確度評估 48
4.1.2 以客戶為導向的協同過濾 50
4.1.3 以產品為導向的協同過濾 54
4.2 交易資料的討論 58
4.2.1 輸入格式 59
4.2.2 相似度計算與推薦方式 62
第5章 結論 64
參考文獻 66
附錄 英文論文 71

Figure 1 協同過濾的處理步驟 24
Figure 2 User-based推薦流程 50
Figure 3 User-based預測評價的輸入 51
Figure 4 User-based的主要預測處理流程 52
Figure 5 User-based的預測結果與整體精確度 53
Figure 6 Item-based推薦流程 54
Figure 7 Item-based預測評價的輸入 55
Figure 8 Item-based的主要預測處理流程 56
Figure 9 Item-based的預測結果與整體精確度 56

Table 2-1 以一組屬性表達餐廳型態 7
Table 2-2 結構化與非結構化資訊之間的差異 9
Table 2-3 CB常見缺點 13
Table 2-4 客戶對產品的評價矩陣 16
Table 2-5 常用評價方式 17
Table 2-6 顯性與隱性評價機制 18
Table 2-7 User對Item的評價矩陣 21
Table 2-8 混合式策略的主要模式 31
Table 2-9 CB與CF之比較 35
Table 3-1 User-based與Item-based相似度比較表 44
參考文獻 [1] M. Pazzani and D. Billsus, "Content-based recommendation systems," The adaptive web, pp. 325-341,2007.
[2] N. J. Belkin and W. B. Croft, "Information filtering and information retrieval: two sides of the same coin?,"Communications of the ACM, vol. 35, pp. 29-38, 1992.
[3] R. Baeza-Yates and B. Ribeiro-Neto, Modern information retrieval vol. 463: ACM press New York., 1999.
[4] G. Adomavicius and A. Tuzhilin, "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, pp. 734-749, 2005.
[5] K. Lang, "Newsweeder: Learning to filter netnews," 1995.
[6] T. Joachims, et al., "Webwatcher: A tour guide for the world wide web," 1997, pp. 770-777.
[7] M. Pazzani and D. Billsus, "Learning and revising user profiles: The identification of interesting web sites," Machine learning, vol. 27, pp. 313-331, 1997.
[8] R. J. Mooney and L. Roy, "Content-based book recommending using learning for text categorization," Arxiv preprint cs/9902011, 1999.
[9] M. Tkal i , et al., "Using affective parameters in a content-based recommender system for images," User Modeling and User-Adapted Interaction, pp. 1-33, 2010.
[10] A. Zenebe and A. F. Norcio, "Representation, similarity measures and aggregation methods using fuzzy sets for content-based recommender systems," Fuzzy Sets and Systems, vol. 160, pp. 76-94, 2009.
[11] J. Schafer, et al., "Collaborative filtering recommender systems," The adaptive web, pp. 291-324, 2007.
[12] K. Ali and W. Van Stam, "TiVo: making show recommendations using a distributed collaborative filtering architecture," 2004, pp. 394-401.
[13] G. Salton, "Automatic text processing: the transformation," Analysis and Retrieval of Information by Computer, 1989.
[14] W. W. Cohen and H. Hirsh, "Joins that generalize: Text classification using whirl," 1998, p. 169!V173.
[15] Y. Yang, "An evaluation of statistical approaches to text categorization," Information retrieval, vol. 1, pp. 69-90, 1999.
[16] J. Allan, et al., "Topic detection and tracking pilot study: Final report," 1998, pp. 194-218.
[17] D. Billsus, et al., "A learning agent for wireless news access," 2000, pp. 33-36.
[18] M. F. Porter, "An algorithm for suffix stripping," Program: electronic library and information systems, vol. 14, pp. 130-137, 1993.
[19] J. J. Rocchio, "Relevance feedback in information retrieval," 1971.
[20] P. W. Foltz and S. T. Dumais, "Personalized information delivery: An analysis of information filtering methods," Communications of the ACM, vol. 35, pp. 51-60, 1992.
[21] S. Loeb, "Architecting personalized delivery of multimedia information," Communications of the ACM, vol. 35, pp. 39-47, 1992.
[22] M. De Gemmis, et al., "Integrating tags in a semantic content-based recommender," 2008, pp. 163-170.
[23] X. N. Lam, et al., "Addressing cold-start problem in recommendation systems," 2008, pp. 208-211.
[24] A. I. Schein, et al., "Methods and metrics for cold-start recommendations," 2002, pp. 253-260.
[25] C. Wartena, et al., "Selecting keywords for content based recommendation," 2010, pp. 1533-1536.
[26] U. Shardanand and P. Maes, "Social information filtering: algorithms for automating !§word of mouth!‥," 1995, pp. 210-217.
[27] D. Billsus and M. J. Pazzani, "User modeling for adaptive news access," User Modeling and User-Adapted Interaction, vol. 10, pp. 147-180, 2000.
[28] J. L. Herlocker, et al., "Explaining collaborative filtering recommendations," 2000, pp. 241-250.
[29] X. Su and T. M. Khoshgoftaar, "A survey of collaborative filtering techniques," Advances in Artificial Intelligence, vol. 2009, p. 4, 2009.
[30] J. B. Schafer, et al., "Recommender systems in e-commerce," 1999, pp. 158-166.
[31] R. Burke, "Hybrid recommender systems: Survey and experiments," User Modeling and User-Adapted Interaction, vol. 12, pp. 331-370, 2002.
[32] J. Delgado and N. Ishii, "Memory-Based Weighted-Majority Prediction," 1999.
[33] P. Resnick, et al., "GroupLens: an open architecture for collaborative filtering of netnews," 1994, pp. 175-186.
[34] AudioScrobbler. Available: http://www.last.fm/index.php
[35] MusicStrands. Available: http://www.musicstrands.com/
[36] V. Zanardi and L. Capra, "Social ranking: uncovering relevant content using tag-based recommender systems," 2008, pp. 51-58.
[37] CiteULike. Available: http://www.citeulike.org/home
[38] D. Goldberg, et al., "Using collaborative filtering to weave an information tapestry," Communications of the ACM, vol. 35, pp. 61-70, 1992.
[39] J. A. Konstan, et al., "GroupLens: applying collaborative filtering to Usenet news," Communications of the ACM, vol. 40, pp. 77-87, 1997.
[40] W. Hill, et al., "Recommending and evaluating choices in a virtual community of use," 1995, pp. 194-201.
[41] K. Goldberg, et al., "Eigentaste: A constant time collaborative filtering algorithm," Information retrieval, vol. 4, pp. 133-151, 2001.
[42] G. Linden, et al., "Amazon. com recommendations: Item-to-item collaborative filtering," Internet Computing, IEEE, vol. 7, pp. 76-80, 2003.
[43] R. M. Bell and Y. Koren, "Lessons from the Netflix prize challenge," ACM SIGKDD Explorations Newsletter, vol. 9, pp. 75-79, 2007.
[44] M. Deshpande and G. Karypis, "Item-based top-n recommendation algorithms," ACM Transactions on Information Systems (TOIS), vol. 22, pp. 143-177, 2004.
[45] B. Sarwar, et al., "Item-based collaborative filtering recommendation algorithms," 2001, pp. 285-295.
[46] L. Candillier, et al., "Comparing state-of-the-art collaborative filtering systems," Machine Learning and Data Mining in Pattern Recognition, pp. 548-562, 2007.
[47] J. L. Herlocker, et al., "An algorithmic framework for performing collaborative filtering," 1999, pp. 230-237.
[48] D. Lemire and A. Maclachlan, "Slope one predictors for online rating-based collaborative filtering," Society for Industrial Mathematics, 2005.
[49] H. C. Kum, et al., "Sequential pattern mining in multi-databases via multiple alignment," Data Mining and Knowledge Discovery, vol. 12, pp. 151-180, 2006.
[50] Amazon. Available: http://www.amazon.com
[51] D. Billsus and M. J. Pazzani, "Learning collaborative information filters," 1998, p. 48.
[52] T. K. Landauer and M. L. Littman, "Computerized cross-language document retrieval using latent semantic indexing," ed: Google Patents, 1994.
[53] S. Deerwester, et al., "Indexing by latent semantic analysis," Journal of the American society for information science, vol. 41, pp. 391-407, 1990.
[54] P. Resnick and H. R. Varian, "Recommender systems," Communications of the ACM, vol. 40, pp. 56-58, 1997.
[55] K. Pearson, "LIII. On lines and planes of closest fit to systems of points in space," Philosophical Magazine Series 6, vol. 2, pp. 559-572, 1901.
[56] J. B. Schafer, et al., "Meta-recommendation systems: user-controlled integration of diverse recommendations," 2002, pp. 43-51.
[57] M. O!|connor, et al., "PolyLens: A recommender system for groups of users," 2001, pp. 199-218.
[58] P. J. Ludford, et al., "Think different: increasing online community participation using uniqueness and group dissimilarity," 2004, pp. 631-638.
[59] R. Torres, et al., "Enhancing digital libraries with TechLens+," 2004, pp. 228-236.
[60] K. H. L. Tso-Sutter, et al., "Tag-aware recommender systems by fusion of collaborative filtering algorithms," 2008, pp. 1995-1999.
[61] I. Konstas, et al., "On social networks and collaborative recommendation," 2009, pp. 195-202.
[62] Y. Koren, "Collaborative filtering with temporal dynamics," Communications of the ACM, vol. 53, pp. 89-97, 2010.
[63] M. O'Mahony, et al., "Collaborative recommendation: A robustness analysis," ACM Transactions on Internet Technology (TOIT), vol. 4, pp. 344-377, 2004.
[64] BBC News Online. Available: http://news.bbc.co.uk/1/hi/entertainment/film/1368666.stm
[65] G. Karypis, "Evaluation of item-based top-n recommendation algorithms," 2001, pp. 247-254.
[66] A. Gunawardana and C. Meek, "A unified approach to building hybrid recommender systems," 2009, pp. 117-124.
[67] M. Zanker, "A collaborative constraint-based meta-level recommender," 2008, pp. 139-146.
[68] G. Lekakos and P. Caravelas, "A hybrid approach for movie recommendation," Multimedia tools and applications, vol. 36, pp. 55-70, 2008.
[69] MovieLens. Available: http://www.movielens.org
[70] Y. H. Lee, et al., "Overcoming small-size training set problem in content-based recommendation: a collaboration-based training set expansion approach," 2009, pp. 99-106.
[71] S. H. Choi, et al., "A hybrid recommendation method with reduced data for large-scale application," Systems, Man, and Cybernetics, Part C: Applications and Reviews, IEEE Transactions on, vol. 40, pp. 557-566, 2010.
[72] Netflix. Available: http://www.netflixprize.com
[73] M. Wu, "Collaborative filtering via ensembles of matrix factorizations," 2007.
[74] A. Albadvi and M. Shahbazi, "A hybrid recommendation technique based on product category attributes," Expert Systems with Applications, vol. 36, pp. 11480-11488, 2009.
[75] Y. J. Park and K. N. Chang, "Individual and group behavior-based customer profile model for personalized product recommendation," Expert Systems with Applications, vol. 36, pp. 1932-1939, 2009.
[76] M. Salganicoff, "Tolerating concept and sampling shift in lazy learning using prediction error context switching," Artificial Intelligence Review, vol. 11, pp. 133-155, 1997.
[77] M. Vuk and T. Curk, "ROC curve, lift chart and calibration plot," Metodoloski zvezki, vol. 3, pp. 89-108, 2006.
[78] A. C. R. van Riel, et al., "Exploring consumer evaluations of e-services: a portal site," International Journal of Service Industry Management, vol. 12, pp. 359-377, 2001.
[79] S. Gauch, et al., "User profiles for personalized information access," The adaptive web, pp. 54-89, 2007.
[80] Hinet. Available: Available: http://www.hinet.net/]
  • 同意紙本無償授權給館內讀者為學術之目的重製使用,於2016-07-19公開。
  • 不同意授權瀏覽/列印電子全文服務。

  • 若您有任何疑問,請與我們聯絡!
    圖書館: 請來電 (02)2621-5656 轉 2487 或 來信 dss@mail.tku.edu.tw