臺灣博碩士論文加值系統

由於電子商務的發展，巨量的商品訊息讓顧客難以找到他們真正想要的商品，因而使得推薦系統成為一個重要的課題。傳統的推薦方法通常利用顧客對於所購買之商品明確表態喜好的資料，例如評分資料，來找出顧客的喜好傾向，以作為推薦的依據。然而顧客們往往不喜歡主動地在網際網路或是購物平台上面留下自己的回饋，使得這類的評分資料難以取得並且也必須面臨資料稀疏的問題。因此，越來越多的研究轉而利用顧客行為紀錄之原始資料作為推薦的依據，這樣的資料被稱為隱含式回饋。然而隱含式回饋只記錄了顧客的使用行為，無法直接反應顧客的喜好程度，使得利用隱含式回饋預測使用者的喜好商品會遠比利用明確表態喜好的資料更加不準確。為了解決在隱含式回饋上推薦不準確的問題，我們提出了一個考慮顧客行為特徵，特別是顧客重複消費行為的情境感知隱含式回饋推薦方法。我們擷取出有效的情境感知特徵資料，綜合這些特徵資料以找出顧客當下潛在的情境，並由此推薦顧客下一個想要購買的商品。這樣的推薦方法不僅是能夠感知顧客當下情境，以提供顧客一個準確且適當的商品推薦，也可以作為搜尋策略以輔助顧客找到其當下最想找尋的商品。而我們所提出的情境感知隱含式回饋推薦方法能夠應用在許多擁有重複消費特性的範疇，例如：網頁瀏覽資料、音樂播放資料、關鍵字搜尋資料甚至是智慧型設備軟體使用記錄…等。我們的方法在重複消費特性的資料上能夠比其他的隱含式推薦方法及情境感知推薦方法提升20%的推薦命中率。

The importance of recommendation systems is increasing since the rise of the e-commerce. It is an efficient way to retrieve wanted data for customers within flood of information. An accurate and efficient recommendation system is helps users to find the product they want more conveniently, which improving the revenue of the e-commerce platform by providing information of interest to customers. However, how to retrieve and use the customer’s using record for building a reliable recommendation system has become an important issue.
There are two kinds of user feedback: explicit feedback and implicit feedback. Traditional recommendation methods collected numeric scores on products as customers’ feedback. The score data is called as explicit feedback. However, this kind of rating score data is rare and very sparse. Therefore, other researches focus on using the original customer records as recommended basis is called implicit feedback. Nonetheless, implicit feedback cannot reflect the customer preferences directly, that cause worse performance in some cases. In this study, we proposed a context-aware recommendation approach to solve the problem of recommendation on implicit feedback. This approach considers the features that identify context extracted from customers’ behaviors, especially on the repeat consumption behaviors. As evaluation, we compare our approach with other implicit feedback recommendation approaches, context-aware recommendation approaches are also compared. Our approach can be applied to several domains, e.g., webpage viewing, music listening, query searching, and usage habits on intelligent devices.

中文摘要 I
ABSTRACT II
TABLE LISTING VI
FIGURE LISTING VII
1. INTRODUCTION 1
1.1 Background 1
1.2 Motivation 5
1.3 Our Approach 8
1.4 Paper Structure 10
2. RELATED WORKS 11
2.1 Implicit Feedback Recommendation 11
2.2 Context-aware Recommendation 13
2.3 Repeat Consumption 15
3. METHOD 16
3.1 Preliminary 16
3.2 Context Features 19
3.2.1 User Repeat Consumption (URC) 20
3.2.2 Item Repeat Consumption (IRC) 21
3.2.3 Item Transition (IT) 21
3.2.4 Novelty Consumption (NC) 22
3.3 Feature Weights Updating 23
4. EXPERIMENTS AND DISCUSSION 25
4.1 Data Description 25
4.2 Comparison Methods 28
4.2.1 Matrix Factorization 28
4.2.2 BPR-MF 28
4.2.3 Tensor Factorization 28
4.2.4 PrefixSpan 29
4.2.5 Single Feature of Our Approach 29
4.3 Evaluation Metric 31
4.4 Experiments Result 32
4.4.1 Analyzation for Experimental Setting 32
4.4.2 Compare Performance to Single Feature 38
4.4.3 Compare Performance to Baselines 39
4.4.4 Running Time Comparison 41
5. CONCLUSION 42
REFERENCE 43

[1]A. Anderson, R. Kumar, A. Tomkins, and S. Vassilvitskii, The dynamics of repeat consumption, in Proceedings of the 23rd international conference on World wide web, 2014, pp. 419-430.
[2]M. Balabanović and Y. Shoham, Fab: content-based, collaborative recommendation, Communications of the ACM, vol. 40, pp. 66-72, 1997.
[3]A. R. Benson, R. Kumar, and A. Tomkins, Modeling User Consumption Sequences, in Proceedings of the 25th International Conference on World Wide Web, 2016, pp. 519-529.
[4]J. S. Breese, D. Heckerman, and C. Kadie, Empirical analysis of predictive algorithms for collaborative filtering, in Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence, 1998, pp. 43-52.
[5]O. Celma, Music recommendation, in Music Recommendation and Discovery, ed: Springer, 2010, pp. 43-85.
[6]J. Chen, C. Wang, and J. Wang, Will You Reconsume the Near Past? Fast Prediction on Short-Term Reconsumption Behaviors, in AAAI, 2015, pp. 23-29.
[7]Y.-C. Chen and H.-Y. Kao, One-Class Recommendation System with PU learning, presented at the Proc. of 6th International Workshop on Social Recommender Systems (SRS 2015), in conjunction with 21st ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2015), 2015.
[8]Y. Chen, X. S. Zhou, and T. S. Huang, One-class SVM for learning in image retrieval, in Image Processing, 2001. Proceedings. 2001 International Conference on, 2001, pp. 34-37.
[9]E. Cho, S. A. Myers, and J. Leskovec, Friendship and mobility: user movement in location-based social networks, in Proceedings of the 17th ACM SIGKDD international conference on Knowledge discovery and data mining, 2011, pp. 1082-1090.
[10]C. Cortes and V. Vapnik, Support-vector networks, Machine learning, vol. 20, pp. 273-297, 1995.
[11]Y. Freund and R. E. Schapire, A desicion-theoretic generalization of on-line learning and an application to boosting, in European conference on computational learning theory, 1995, pp. 23-37.
[12]N. Hariri, B. Mobasher, and R. Burke, Context-aware music recommendation based on latenttopic sequential patterns, in Proceedings of the sixth ACM conference on Recommender systems, 2012, pp. 131-138.
[13]B. Hidasi and D. Tikk, Fast ALS-based tensor factorization for context-aware recommendation from implicit feedback, in Joint European Conference on Machine Learning and Knowledge Discovery in Databases, 2012, pp. 67-82.
[14]Y. Hu, Y. Koren, and C. Volinsky, Collaborative filtering for implicit feedback datasets, in 2008 Eighth IEEE International Conference on Data Mining, 2008, pp. 263-272.
[15]S. Huang, S. Wang, T.-Y. Liu, J. Ma, Z. Chen, and J. Veijalainen, Listwise Collaborative Filtering, in Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, 2015, pp. 343-352.
[16]A. Karatzoglou, X. Amatriain, L. Baltrunas, and N. Oliver, Multiverse recommendation: n-dimensional tensor factorization for context-aware collaborative filtering, in Proceedings of the fourth ACM conference on Recommender systems, 2010, pp. 79-86.
[17]Y. Koren, R. Bell, and C. Volinsky, Matrix factorization techniques for recommender systems, Computer, vol. 42, pp. 30-37, 2009.
[18]B. Liu, Web data mining: exploring hyperlinks, contents, and usage data: Springer Science ＆ Business Media, 2007.
[19]N. N. Liu, E. W. Xiang, M. Zhao, and Q. Yang, Unifying explicit and implicit feedback for collaborative filtering, in Proceedings of the 19th ACM international conference on Information and knowledge management, 2010, pp. 1445-1448.
[20]L. M. Manevitz and M. Yousef, One-class SVMs for document classification, Journal of Machine Learning Research, vol. 2, pp. 139-154, 2001.
[21]R. Pan, Y. Zhou, B. Cao, N. N. Liu, R. Lukose, M. Scholz, et al., One-class collaborative filtering, in 2008 Eighth IEEE International Conference on Data Mining, 2008, pp. 502-511.
[22]M. J. Pazzani and D. Billsus, Content-based recommendation systems, in The adaptive web, ed: Springer, 2007, pp. 325-341.
[23]D. M. Pennock, E. Horvitz, S. Lawrence, and C. L. Giles, Collaborative filtering by personality diagnosis: A hybrid memory-and model-based approach, in Proceedings of the Sixteenth conference on Uncertainty in artificial intelligence, 2000, pp. 473-480.
[24]S. Rendle, C. Freudenthaler, Z. Gantner, and L. Schmidt-Thieme, BPR: Bayesian personalized ranking from implicit feedback, in Proceedings of the twenty-fifth conference on uncertainty in artificial intelligence, 2009, pp. 452-461.
[25]P. Resnick, N. Iacovou, M. Suchak, P. Bergstrom, and J. Riedl, GroupLens: an open architecture for collaborative filtering of netnews, in Proceedings of the 1994 ACM conference on Computer supported cooperative work, 1994, pp. 175-186.
[26]B. Sarwar, G. Karypis, J. Konstan, and J. Riedl, Item-based collaborative filtering recommendation algorithms, in Proceedings of the 10th international conference on World Wide Web, 2001, pp. 285-295.
[27]J. B. Schafer, D. Frankowski, J. Herlocker, and S. Sen, Collaborative filtering recommender systems, in The adaptive web, ed: Springer, 2007, pp. 291-324.
[28]A. I. Schein, A. Popescul, L. H. Ungar, and D. M. Pennock, Methods and metrics for cold-start recommendations, in Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval, 2002, pp. 253-260.
[29]G. Shani, D. Heckerman, and R. I. Brafman, An MDP-based recommender system, Journal of Machine Learning Research, vol. 6, pp. 1265-1295, 2005.