In this thesis, we propose a new framework on Dynamic Collaborative Filtering based on the decay of similarities among users in order to solve the unreasonable pheromone of other Dynamic Collaborative Filtering works. The experimental results show that our proposed method has higher accuracies on both MAE and precision/recall measurements.
In the other words, our predictions present well on both of the items which users potentially have interests or not. This ensures our predictions satisfy some users who have special interests. Furthermore, the results show that our assumption, people do not actually change their favors on an item but the similarities among people change because of time, is correct. In our architecture we divide the data into several segments. This manner not only supports incremental similarity calculation, but reduces the repeated computation of old data. Thus, our work fits real-time property better than other works and also be more appropriate in practice.
For the future work, we have some suggestions:
(1) We want to design formulas for dynamic CF. In our work, the similarities and prediction calculation formulas are the same as traditional CF. The formulas are designed as static, in other words, they have no time factor. We achieve dynamic property by multiplying a decay coefficient on similarities. We believe that a well-designed dynamic formula will not only raise the accuracies but also improve the execution performance.
(2) Practically, a Recommendation System should be hybrid-based. Because the complexity of human-behavior and various items in the system, it has to cooperate with many analyzed algorithms to reinforce the accuracy. Nonetheless, too many calculations may cause lower performance. Accordingly, we look forward to develop a well-designed hybrid-based Recommendation System.
40
Bibliography
[1] G. Adomavicius and A. Tuzhilin, “Toward the Next Generation of Recommender System: A Survey of the State-of-the-Art and Possible Extensions,” IEEE Transactions Knowledge and Data Eng., vol.18, no.6, pp. 734-749, 2005.
[2] M. Balabanvic and Y. Shoham, “Fab: Content-based, Collaborative Recommendation,” Comm. ACM, vol.40, no. 3, pp. 66-72, 1997.
[3] I. Bartolini, Z. Zhang, and D. Papadias, “Collaborative Filtering with Personalized Skylines,” Knowledge and Data Engineering, IEEE Transactions, vol. 23, Issue 2, pp. 190 – 203, 2011.
[4] J. Breese, D. Heckerman and C. Kadie, “Empirical Analysis of Predictive Algorithm for Collaborative Filtering,” Proc. 14th Conf. Uncertainty in Artificial Intelligence, 1998.
[5] R. Burke, ”Hybrid web recommender systems,” The Adaptive Web LNCS, vol.
4321, pp. 377–408, 2007.
[6] R. Burke, “Hybrid Recommender Systems: Survey and Experiments,” User modeling and user-adapted interaction, vol. 12, Number 4, pp. 331-370, 2002.
[7] T. Chen, W. Han, H.Wang, Y. Zhou, B. Xu and B. Zang, “Content recommendation system based on private dynamic user profile,” Machine Learning and Cybernetics, vol. 4, pp. 2112 – 2118, 2007.
[8] M. Claypool, A. Gokhale, and T. Miranda, “Combining content-based and collaborative filters in an online newspaper, ” Proc. of the ACM SIGIR-99 workshop on recommender systems-implementation and evaluation, 1999.
[9] Y. Ding, X. Li and M. Orlowska, “Recency-based collaborative filtering,”
Proceedings of the 17th Australasian Database Conference, vol. 49, pp. 99-107, 2006.
41
[10] Y. Ding and X. Li, “Time weight Collaborative Filtering,” Proceedings of the 14th ACM international conference on Information and knowledge management, pp.
485 – 492, 2005.
[11] D. Goldberg, D. Nichols, B. Oki and D. Terry, “Using Collaborative Filtering to weave an information tapestry,” Communications of the ACM - Special issue on information filtering, vol. 35, Issue 12, pp. 61 – 70, 1992.
[12] J. Herlocker, J. Konstan and J. Riedl, “An empirical analysis of design choices in neighborhood-based collaborative filtering systems,” Information Retrieval, pp.
287–310, 2002.
[13] T. Hofmann, “Collaborative Filtering via Gaussian Probabilistic Latent Semantic Analysis,” Proceedings of the 26th annual international ACM SIGIR conference of Research and Development in Information retrieval, pp. 259-266, 2003.
[14] I. Konstas , V. Stathopoulos and J. Jose, “On social networks and collaborative recommendation,” The 32nd international ACM SIGIR conference on Research and development in information retrieval, pp. 195-202,2009.
[15] Y. Koren, R. Bell and C. Volinsky, “Factorization Techniques for Recommender Systems,” Computer, vol. 42, Issue 8, pp. 30 – 37, 2009.
[16] M. L., C. N. and J.D.J. Perez-Alcazar, “A comparison of several predictive algorithms for collaborative filtering on multi-valued ratings,” ACM symposium on Applied computing, pp. 1033-1039, 2004.
[17] Q. Li and M. Zhou, “Research and design of an efficient collaborative filtering predication algorithm,” Parallel and Distributed Computing, applications and technologies, pp. 171-174, 2003.
[18] G. Linden, B. Smith and J. York, “Amazon.com recommendations: item-to-item Collaborative Filtering,” Internet Computing IEEE, vol. 7, Issue 1, pp.76-80, 2003.
[19] C. Liu and J. Cheng, “Personalized Search Recommendation Based on Gradual
42
Forgetting Collaborative Filtering Strategy,” Intelligent Information Technology Application, pp. 475-478, 2009.
[20] Q. Liu, E. Chen, H. Xiong, C. Ding and J. Chen, “Enhancing Collaborative Filtering by User Interest Expansion via Personalized Ranking,” Systems, Man, and Cybernetics, Part B: Cybernetics, IEEE Transactions, vol. 42, Issue 1, pp. 218 – 233, 2012.
[21] S. Lo and C. Lin, “WMR-A graph-based algorithm for friend recommendation,”
Proceedings of IEEE/WIC/ACM International Conference on Web Intelligence, pp.
121–128, 2006.
[22] M. Pazzani, “A Framework for Collaborative, Content-Based and Demographic Filtering,” ARTIFICIAL INTELLIGENCE REVIEW, vol. 13, Numbers 5-6, pp. 393-408, 1999.
[23] T. Peng, W. Wang, X. Gong, Y. Tian, X. Yang and J. Ma, “A Graph Indexing Approach for Content-Based Recommendation System,” Multimedia and Information Technology (MMIT), vol. 1, pp. 93 – 97, 2010.
[24] P. Resnick, N. Iacovou, M. Suchak, P. Bergstorm and J. Ried, “Grouplens: an open architecture for collaborative filtering of netnews,” ACM conference on Computer supported cooperative work, pp. 175-186, 1194.
[25] B. Sarwar, G. Karypis, J. Konstan and J. Riedl, “Item-Based collaborative Filtering recommendation systems,” International World Wide Web Conference, pp. 285-295, 2001.
[26] J. Schafer, J. Konstan and J. Riedl, “E-Commerce Recommendation Applications,”
Data Mining and Knowledge Discovery, vol. 5, Numbers 1-2, pp. 115–153, 2001.
[27] L. Si and R. Jin, “Flexible Mixture Model for Collaborative Filtering,” Twentieth international conference on machine learning, Washington DC, 2003.
[28] H. Tan and H. Ye, “A Collaborative Filtering Recommendation Algorithm Based
43
On Item Classification,” Computing in the Global Information Technology (ICCGI), Fifth International Multi-Conference, pp. 66 – 70, 2010.
[29] T. Tang, P. Winoto and K. Chan, “On the Temporal Analysis for Improved Hybrid Recommendations,” Web Intelligence, pp. 214-220, 2003.
[30] Z. Wang, Y. Tan and M. Zhang,”Graph-based recommendation on social networks,”
Proceedings of International Asia–Pacific Web Conference, pp. 116–122. , 2010.
[31] R. Wong, J. Pei,, A. Fu and K. Wang, “Mining Favorable Facets,” Proc. 13th ACM SIGKDD Int’l Conf. Knowledge Discovery and Data Mining, 2007.
[32] C. Xia, X. Jiang, S. Liu, Z. Luo and Z. Yu, “Dynamic Item-Based Recommendation Algorithm with Time Decay,” Natural Computation (ICNC),Sixth International Conference, pp. 242-247, 2010.
[33] S. Yu, ”The dynamic competitive recommendation algorithm in social network services,” Information Sciences, vol. 187, pp. 1–14, 2012.
[34] C. Zeng, C. Xing and L. Zhou, “Similarity measure and instance selection for collaborative filtering,” Proceedings of the 12th international conference on World Wide Web, pp. 652 – 658, 2003.
[35] C. Ziegler, G. Lausen and L. THieme, “Taxonomy-driven Computation of Product Recommendations,” Proceedings of the thirteenth ACM international conference on Information and knowledge management, pp. 406 – 415, 2004.
[36] Y. Zhao, C. Zhang and S. Zhang, “A Recent-Biased Dimension Reduction Technique for Time Series Data,“ Advances in knowledge discovery and data mining, Lecture Notes in Computer Science, vol. 3518, pp. 107-176, 2005.
[37] “MovieLens,” http://www.grouplens.org/node/73/
[38] “Netflix,” http://www.netflixprize.com/