近年來，隨著行動裝置的技術進步，只要使用者一有購買需求，使用者就能隨時隨地地在電子商務網站進行購買。即時推薦系統存在的目的為根據使用者即時的需求準確地為他/她推薦適合的選項或者是產品，並且系統能越早推測使用者的的需求越好。而且，使用者的及時需求不一定和他/她原本長期瀏覽記錄所推測出來的喜好一致。然而，之前對於即時推薦系統的研究主要針對使用者的喜好，而非使用者即時意圖，也就是即時的需求，有太多的著墨。為了研究使用者即時的需求，我們探討了使用者即時需求是如何影響短時間內的點擊行為。經我們觀察研究發現，如果推薦系統想要更精準地推薦符合使用者即時意圖的選項，系統除了要根據此次瀏覽點擊的所有項目進行推薦，更應該要即時追蹤使用者即時意圖。然而，先前的研究若要精準的根據使用者的即時需求推薦會面臨執行時間和效率的挑戰。受到了這個觀察的啟發，我們此次的研究提出了一個點擊更新的推薦模型，此模型不但可以即時追從使用者的意圖，並且透過使用者此次瀏覽時間內所有點擊的項目，使得推薦符合使用者即時意圖。為了利用點擊更新推薦模型，我們設計了一個演算法，此演算法利用隨機走路的方式，有效率地線上偵測此次瀏覽的意圖。我們實驗結果顯示，利用電子商務網站所提供的三千多萬筆真實資料，我們方法推薦效能或者是面對巨量資料的時候都能表現比先前文獻的方法。

Recently, the advance of mobile devices empowers users to purchase in the e-commerce marketplace at all times when they have any instant requirement. The real-time recommender systems should aim to recommend items in response to the current user intent, i.e. instant user needs, accurately predicting the finally purchased items as early as possible. Note that the instant user need is not always aligned with her/his long-term favorites that are revealed in the visited history.However, previous
works about real-time recommender systems paid much attention to the user preferenceinstead of the instant user intent. To study user intent in a real-time environment, we explore thoroughly how instant user intent can be related to click sequences. We found that to accurately capture user intent, the system not only has to recommend items based on the clicked items in a session, but also has to track the implicit user intent
in real-time. If the previous works want to recommend with instant user needs, they will have enormous execution overheads. Motivated by this, we propose in this paper a intent-tracking model that tracks the user intent and recommends items aligned with user intent by checking all items visited from the beginning of the session. To facilitate the framework, we further devised a recommending algorithm to efficiently capture the instant user intent through the random walk manner. As shown in our experimental results with a real dataset from an e-commerce vendor with 33M click events, the recommendation quality and scalability of the proposed models outperform state-of-the-art methods.

[1] G. Adomavicius and A. Tuzhilin. Toward the next generation of recommender
systems: A survey of the state-of-the-art and possible extensions. IEEE Trans.
Knowl. Data Eng., 17(6):734–749, 2005.
[2] D. Agarwal, B. Chen, and P. Elango. Fast online learning through offline initialization
for time-sensitive recommendation. In Proceedings of the 16th ACM
SIGKDD International Conference on Knowledge Discovery and Data Mining,
pages 703–712, 2010.
[3] C. C. Aggarwal and S. Parthasarathy. Mining massively incomplete data sets by
conceptual reconstruction. In Proceedings of the 7th ACM SIGKDD International
Conference on Knowledge Discovery and Data Mining, pages 227–232, 2001.
[4] R. Agrawal, T. Imielinski, and A. N. Swami. Mining association rules between
sets of items in large databases. In Proceedings of the 1993 ACM SIGMOD International
Conference on Management of Data, pages 207–216, Dec 1993.
[5] D. Ben-Shimon, A. Tsikinovsky, M. Friedmann, B. Shapira, L. Rokach, and J. Hoerle.
Recsys challenge 2015 and the YOOCHOOSE dataset. In Proceedings of the
9th ACM RecSys Conference on Recommender Systems, pages 357–358, 2015.
[6] 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, pages 43–52, 1998.
[7] B. Chandramouli, J. J. Levandoski, A. Eldawy, and M. F. Mokbel. Streamrec:
a real-time recommender system. In Proceedings of the 2011 ACM SIGMOD
International Conference on Management of Data, pages 1243–1246, Jun 2011.
[8] C. Cooper, S. Lee, T. Radzik, and Y. Siantos. Random walks in recommender systems:
exact computation and simulations. In Proceedings of the 23rd International
Conference on World Wide Web, WWW, pages 811–816, April 2014.
[9] N. Craswell and M. Szummer. Random walks on the click graph. In Proceedings
of the 30th ACM SIGIR Conference on Research and Development in Information
Retrieval, pages 239–246, July 2007.
[10] A. Das, M. Datar, A. Garg, and S. Rajaram. Google news personalization: scalable
online collaborative filtering. In Proceedings of the 16th International Conference
on World Wide Web, WWW, pages 271–280, May 2007.
[11] J. Dean and S. Ghemawat. Mapreduce: simplified data processing on large clusters.
Commun. ACM, 51(1):107–113, 2008.
[12] M. Deshpande and G. Karypis. Item-based top-n recommendation algorithms.
ACM Trans. Inf. Syst., 22(1):143–177, Jan 2004.
[13] E. Diaz-Aviles, L. Drumond, L. Schmidt-Thieme, and W. Nejdl. Real-time top-n
recommendation in social streams. In Proceedings of the 6th ACM RecSys Conference
on Recommender Systems, pages 59–66, 2012.
[14] M. D. Ekstrand, J. T. Riedl, and J. A. Konstan. Collaborative filtering recommender
systems. Found. Trends Hum.-Comput. Interact., pages 81–173, Feb 2011.
[15] J. L. Herlocker, J. A. Konstan, A. Borchers, and J. Riedl. An algorithmic framework
for performing collaborative filtering. In Proceedings of the 22nd ACM SIGIR
Conference on Research and Development in Information Retrieval, pages
230–237, August 1999.
[16] J. L. Herlocker, J. A. Konstan, and J. Riedl. Explaining collaborative filtering
recommendations. In Proceedings of the 2000 ACM Conference on Computer
Supported Cooperative Work, pages 241–250, 2000.
[17] T. Hofmann. Latent semantic models for collaborative filtering. ACM Trans. Inf.
Syst., pages 89–115, Jan 2004.
[18] Y. Huang, B. Cui, W. Zhang, J. Jiang, and Y. Xu. Tencentrec: Real-time stream
recommendation in practice. In Proceedings of the 2015 ACM SIGMOD International
Conference on Management of Data, pages 227–238, May 2015.
[19] N. Kawamae. Real time recommendations from connoisseurs. In Proceedings of
the 21th ACM SIGKDD International Conference on Knowledge Discovery and
Data Mining, pages 537–546, August 2015.
[20] Y. Koren. Factorization meets the neighborhood: A multifaceted collaborative filtering
model. In Proceedings of the 14th ACM SIGKDD International Conference
on Knowledge Discovery and Data Mining, pages 426–434, 2008.
[21] Y. Koren, R. Bell, and C. Volinsky. Matrix factorization techniques for recommender
systems. Computer, pages 30–37, 2009.
[22] G. Linden, B. Smith, and J. York. Amazon.com recommendations: Item-to-item
collaborative filtering. IEEE Internet Computing, 7(1):76–80, 2003.
[23] L. Page, S. Brin, R. Motwani, and T. Winograd. The pagerank citation ranking:
Bringing order to the web. Technical Report 1999-66, Stanford InfoLab, November
1999.
[24] M. J. Pazzani and D. Billsus. The Adaptive Web: Methods and Strategies of Web
Personalization, chapter Content-Based Recommendation Systems, pages 325–
341. Springer Berlin Heidelberg, 2007.
[25] S. Qi, D. Wu, and N. Mamoulis. Location aware keyword query suggestion based
on document proximity. IEEE Trans. Knowl. Data Eng., 28(1):82–97, 2016.
[26] S. Rendle and L. Schmidt-Thieme. Online-updating regularized kernel matrix
factorization models for large-scale recommender systems. In Proceedings of the
2008 ACM RecSys Conference on Recommender Systems, pages 251–258, Octobber
2008.
[27] 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, pages 175–186, 1994.
[28] B. M. Sarwar, G. Karypis, J. A. Konstan, and J. Riedl. Item-based collaborative
filtering recommendation algorithms. In Proceedings of the 10th International
Conference on World Wide Web, WWW, pages 285–295, May 2001.
[29] U. Shardanand and P. Maes. Social information filtering: Algorithms for automating
“word of mouth”. In Proceedings of the SIGCHI Conference on
Human Factors in Computing Systems, pages 210–217, 1995.
[30] P. Tan, M. Steinbach, and V. Kumar. Introduction to Data Mining. Addison-
Wesley, 2005.
[31] R. Weber, H.-J. Schek, and S. Blott. A quantitative analysis and performance
study for similarity-search methods in high-dimensional spaces. In Proceedings
of the 24rd International Conference on Very Large Data Bases, pages 194–205,
1998.
[32] L. Xiang, Q. Yuan, S. Zhao, L. Chen, X. Zhang, Q. Yang, and J. Sun. Temporal
recommendation on graphs via long- and short-term preference fusion. In Proceedings
of the 16th ACM SIGKDD International Conference on Knowledge Discovery
and Data Mining, pages 723–732, July 2010.
[33] C. Yang, X. Yu, and Y. Liu. Continuous KNN join processing for real-time recommendation.
In Proceedings of the 2014 IEEE ICDM International Conference
on Data Mining, pages 640–649, Mar 2014.
[34] H. Yildirim and M. S. Krishnamoorthy. A random walk method for alleviating
the sparsity problem in collaborative filtering. In Proceedings of the 2008 ACM
RecSys Conference on Recommender Systems, pages 131–138, October 2008.
[35] H. Yin, B. Cui, J. Li, J. Yao, and C. Chen. Challenging the long tail recommendation.
PVLDB, 5(9):896–907, 2012.
[36] A. W. Yu, N. Mamoulis, and H. Su. Reverse top-k search using random walk with
restart. PVLDB, 7(5):401–412, 2014.