隨著科技進步，人們幾乎可以透過網路辦到任何事情，當中最多人使用的便是線上購物和影音串流了。這些平台提供了各式各樣的選擇，然而這麼多的選擇有時候反而會造成使用者在找尋上的困難。因此我們需要推薦系統為我們先找出那些我們比較喜歡的商品。傳統的推薦系統透過使用者提供的資料，像是註冊會員時填的資料或是使用者針對某些商品給予的評分來幫助使用者找到符合他喜好的商品，然而人們通常不會主動提供這些資訊，無論是基於隱私還是懶惰，推薦系統都因為在資料上的匱乏而無法推薦使用者真正感興趣的商品。因此很多研究開始針對使用者的行為或是習慣進行分析，試圖透過觀察使用者而非詢問使用者的方式來推薦，而這些行為的資訊我們稱之為隱涵式回饋，因為是透過觀察及記錄得到的資訊，使用者在提供這些資訊時並不會產生額外的負擔，在資訊的數量上自然比使用者主動提供的資來來的多。然而因為這些資料並沒有經過使用者作出明確的解釋，推薦系統在使用上的難度也增加了。
我們提出了一個基於排序學習的方法，透過不同回饋間的強度比較預測使用者對各個商品的喜好度排序，當中加入了較少研究使用的負面回饋做為比較對象，我們認為在正面和負面回饋之間的關係會比相同面相之間的關係來的明確，再以這種較為明確的關係為主體，提升預測使用者喜好時的準確度。這種推薦方式可以應用在很多不同的地方，只要能合理定義出不同回饋之間的強弱就能夠應用在這種方法上。

Thanks to the advance in technology, there are many kinds of online services for us. Among them, e-commerce, audio and video streaming are the most popular ones. These platforms provide a huge amount of goods for customers, but customers also feel confused to choose something from these choices. Thus we need a recommendation system to help us to find out what we might need or like. Traditional recommendation systems utilize user’s explicit information, like the member profile and the score rated by users. It is hard to collect great amount of this kind of data because people are lazy to give feedback. Moreover, the performance of recommendation will decrease seriously due to the sparsity of dataset.
To solve this problem, more and more researches start to infer users’ preference by analyze their behavior. Many companies start to collect user’s behavior records, such as clicking and browsing time. We get this kind of data by observing user’s actions, that are easier to collect than explicit feedback. It is called implicit feedback because we don’t know the preference extent of users from this data.
In this paper, we propose a ranking based recommendation system. We rank the items by comparing the items with users’ feedback, and we suppose the relation between positive and implicit negative feedback is more feasible than the relation between the same kind of feedbacks. Thus we utilize this relation as the basis of our ranking method to improve the accuracy of our recommendation. Eventually, we increase the performance of recommendation and obtain the result which is more discriminative than the other approaches with implicit feedback.

[1] M. Balabanovi and Y. Shoham, "Fab: content-based, collaborative recommendation" Commun. ACM, pp. 66-72, 1997
[2] J. S. Breese, D. Heckerman and C. Kadie, "Empirical analysis of predictive algorithms for collaborative filtering" Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence, pp. 43-52, 1998
[3] O. Chapelle and M. Wu, "Gradient descent optimization of smoothed information retrieval metrics" Inf. Retr., pp. 216-235, 2010
[4] Y. Hu, Y. Koren and C. Volinsky, "Collaborative Filtering for Implicit Feedback Datasets" Proceedings of the 2008 Eighth IEEE International Conference on Data Mining, pp. 263-272, 2008
[5] S. Huang, S. Wang, T.-Y. Liu, J. Ma, Z. Chen and J. Veijalainen, "Listwise Collaborative Filtering" Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 343-352, 2015
[6] C. C. Johnson, "Logistic Matrix Factorization for Implicit Feedback Data" Proceedings of the 20th Workshop on Distributed Machine Learning and Matrix Computations at Neural Information Processing Systems, 2014
[7] Y. Koren, R. Bell and C. Volinsky, "Matrix Factorization Techniques for Recommender Systems" Computer, pp. 30-37, 2009
[8] Y. Koren and J. Sill, "OrdRec: an ordinal model for predicting personalized item rating distributions" Proceedings of the fifth ACM conference on Recommender systems, pp. 117-124, 2011
[9] D. H. Lee and P. Brusilovsky, "Reinforcing Recommendation Using Implicit Negative Feedback" Proceedings of the 17th International Conference on User Modeling, Adaptation, and Personalization: formerly UM and AH, pp. 422-427, 2009
[10] V. Leksin and A. Ostapets, "Job recommendation based on factorization machine and topic modelling" Proceedings of the Recommender Systems Challenge, pp. 1-4, 2016
[11] C. H. Lin, E. Kamar and E. Horvitz, "Signals in the silence: models of implicit feedback in a recommendation system for crowdsourcing" Proceedings of the Twenty-Eighth AAAI Conference on Artificial Intelligence, pp. 908-914, 2014
[12] N. N. Liu, E. W. Xiang, M. Zhao and Q. Yang, "Unifying explicit and implicit feedback for collaborative filtering" Proceedings of the 19th ACM international conference on Information and knowledge management, pp. 1445-1448, 2010
[13] J. McAuley, C. Targett, Q. Shi and A. v. d. Hengel, "Image-Based Recommendations on Styles and Substitutes" Proceedings of the 38th International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 43-52, 2015
[14] R. Pan, Y. Zhou, B. Cao, N. N. Liu, R. Lukose, M. Scholz and Q. Yang, "One-Class Collaborative Filtering" Proceedings of the 2008 Eighth IEEE International Conference on Data Mining, pp. 502-511, 2008
[15] M. J. Pazzani and D. Billsus, "Content-based recommendation systems" in The adaptive web, pp. 325-341, 2007
[16] D. M. Pennock, E. Horvitz, S. Lawrence and C. L. Giles, "Collaborative Filtering by Personality Diagnosis: A Hybrid Memory and Model-Based Approach" Proceedings of the 16th Conference on Uncertainty in Artificial Intelligence, pp. 473-480, 2000
[17] L. Peska and P. Vojtas, "Negative implicit feedback in e-commerce recommender systems" Proceedings of the 3rd International Conference on Web Intelligence, Mining and Semantics, pp. 1-4, 2013
[18] A. Popescul, D. M. Pennock and S. Lawrence, "Probabilistic models for unified collaborative and content-based recommendation in sparse-data environments" Proceedings of the Seventeenth conference on Uncertainty in artificial intelligence, pp. 437-444, 2001
[19] S. Rendle, C. Freudenthaler, Z. Gantner and L. Schmidt-Thieme, "BPR: Bayesian personalized ranking from implicit feedback" Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence, pp. 452-461, 2009
[20] P. Resnick, N. Iacovou, M. Suchak, P. Bergstrom and J. Riedl, "GroupLens: an open architecture for collaborative filtering of netnews" Proceedings of the 1994 ACM conference on Computer supported cooperative work, pp. 175-186, 1994
[21] S. Roy and S. C. Guntuku, "Latent Factor Representations for Cold-Start Video Recommendation" Proceedings of the 10th ACM Conference on Recommender Systems, pp. 99-106, 2016
[22] B. Sarwar, G. Karypis, J. Konstan and J. Riedl, "Item-based collaborative filtering recommendation algorithms" Proceedings of the 10th international conference on World Wide Web, pp. 285-295, 2001
[23] J. B. Schafer, D. Frankowski, J. Herlocker and S. Sen, "Collaborative filtering recommender systems" in The adaptive web, pp. 291-324, 2007
[24] A. I. Schein, A. Popescul, L. H. Ungar and D. M. Pennock, "Methods and metrics for cold-start recommendations" Proceedings of the 25th annual international ACM SIGIR conference on Research and development in information retrieval, pp. 253-260, 2002
[25] Y. Shi, M. Larson and A. Hanjalic, "List-wise learning to rank with matrix factorization for collaborative filtering" Proceedings of the fourth ACM conference on Recommender systems, pp. 269-272, 2010
[26] Y. Shi, A. Karatzoglou, L. Baltrunas, M. Larson, N. Oliver and A. Hanjalic, "CLiMF: learning to maximize reciprocal rank with collaborative less-is-more filtering" Proceedings of the sixth ACM conference on Recommender systems, pp. 139-146, 2012
[27] Y. Shi, A. Karatzoglou, L. Baltrunas, M. Larson and A. Hanjalic, "xCLiMF: Optimizing Expected Reciprocal Rank for Data with Multiple Levels of Relevance" 2013
[28] L. P. P. Vojtas, "Using Implicit Preference Relations to Improve Recommender Systems" Journal on Data Semantics, pp. 15-30, 2017
[29] E. M. Voorhees, "The TREC-8 Question Answering Track Report" In TREC-8, pp. 77, 1999
[30] M. Weimer, A. Karatzoglou, Q. V. Le and A. Smola, "Cofirank - Maximum Margin Matrix Factorization for collaborative ranking" Proceedings of the 20th International Conference on Neural Information Processing Systems, pp. 1593-1600, 2007
[31] S.-H. Yang, B. Long, A. J. Smola, H. Zha and Z. Zheng, "Collaborative competitive filtering: learning recommender using context of user choice" Proceedings of the 34th international ACM SIGIR conference on Research and development in Information Retrieval, pp. 295-304, 2011