ABSTRACT
A new paradigm of recommendation is emerging in intelligent personal assistants such as Apple's Siri, Google Now, and Microsoft Cortana, which recommends "the right information at the right time" and proactively helps you "get things done". This type of recommendation requires precisely tracking users' contemporaneous intent, i.e., what type of information (e.g., weather, stock prices) users currently intend to know, and what tasks (e.g., playing music, getting taxis) they intend to do. Users' intent is closely related to context, which includes both external environments such as time and location, and users' internal activities that can be sensed by personal assistants. The relationship between context and intent exhibits complicated co-occurring and sequential correlation, and contextual signals are also heterogeneous and sparse, which makes modeling the context intent relationship a challenging task. To solve the intent tracking problem, we propose the Kalman filter regularized PARAFAC2 (KP2) nowcasting model, which compactly represents the structure and co-movement of context and intent. The KP2 model utilizes collaborative capabilities among users, and learns for each user a personalized dynamic system that enables efficient nowcasting of users' intent. Extensive experiments using real-world data sets from a commercial personal assistant show that the KP2 model significantly outperforms various methods, and provides inspiring implications for deploying large-scale proactive recommendation systems in personal assistants.
Supplemental Material
- http://www.google.com/landing/now/.Google Scholar
- http://dev.windows.com/en-us/cortana.Google Scholar
- http://www.apple.com/ios/whats-new/.Google Scholar
- G. Adomavicius and A. Tuzhilin. Context-aware recommender systems. In Recommender systems handbook, pages 217--253. Springer, 2011. Google ScholarDigital Library
- M. M. Banbura, D. Giannone, and L. Reichlin. Nowcasting. The Oxford Handbook of Economic Forecasting, 2012.Google Scholar
- R. M. Bell and Y. Koren. Lessons from the netflix prize challenge. KDD Explorations, 9(2):75--79, 2007. Google ScholarDigital Library
- Y. Cai, H. Tong, W. Fan, P. Ji, and Q. He. Facets: Fast comprehensive mining of coevolving high-order time series. In KDD, pages 79--88, 2015. Google ScholarDigital Library
- O. Celma. Music recommendation. Springer, 2010.Google ScholarDigital Library
- D. Giannone, L. Reichlin, and D. Small. Nowcasting: The real-time informational content of macroeconomic data. Journal of Monetary Economics, 55(4):665--676, 2008.Google ScholarCross Ref
- R. Guha, V. Gupta, V. Raghunathan, and R. Srikant. User modeling for a personal assistant. In WSDM, pages 275--284, 2015. Google ScholarDigital Library
- R. A. Harshman. Parafac2: Mathematical and technical notes. UCLA Working Papers in Phonetics, 22(3044):122215, 1972.Google Scholar
- D. Jannach, L. Lerche, and M. Jugovac. Adaptation and evaluation of recommendations for short-term shopping goals. In RecSys, pages 211--218, 2015. Google ScholarDigital Library
- A. Karatzoglou, X. Amatriain, L. Baltrunas, and N. Oliver. Multiverse recommendation: N-dimensional tensor factorization for context-aware collaborative filtering. In RecSys, pages 79--86, 2010. Google ScholarDigital Library
- T. G. Kolda and B. W. Bader. Tensor decompositions and applications. SIAM review, 51(3):455--500, 2009. Google ScholarDigital Library
- Y. Koren. Collaborative filtering with temporal dynamics. In KDD, pages 447--456, 2009. Google ScholarDigital Library
- V. Lampos and N. Cristianini. Nowcasting events from the social web with statistical learning. TIST, 3(4):72, 2012. Google ScholarDigital Library
- Q. Liu, H. Ma, E. Chen, and H. Xiong. A survey of context-aware mobile recommendations. International Journal of Information Technology & Decision Making, 12(01):139--172, 2013.Google ScholarCross Ref
- J. R. Magnus, H. Neudecker, et al. Matrix differential calculus with applications in statistics and econometrics.Google Scholar
- R. J. Mooney and L. Roy. Content-based book recommending using learning for text categorization. In Proceedings of the fifth ACM conference on Digital libraries, pages 195--204, 2000. Google ScholarDigital Library
- S. Rendle, C. Freudenthaler, and L. Schmidt-Thieme. Factorizing personalized markov chains for next-basket recommendation. In WWW, pages 811--820, 2010. Google ScholarDigital Library
- M. Shokouhi and Q. Guo. From queries to cards: Re-ranking proactive card recommendations based on reactive search history. In SIGIR, pages 695--704, 2015. Google ScholarDigital Library
- Y. Sun, N. J. Yuan, X. Xie, K. McDonald, and R. Zhang. Collaborative nowcasting for contextual recommendation. In WWW, pages 1407--1418, 2016. Google ScholarDigital Library
- Z. Wang, P. Chakraborty, S. R. Mekaru, J. S. Brownstein, J. Ye, and N. Ramakrishnan. Dynamic poisson autoregression for influenza-like-illness case count prediction. In KDD, pages 1285--1294, 2015. Google ScholarDigital Library
- Y. Zhang, M. Zhang, Y. Zhang, G. Lai, Y. Liu, H. Zhang, and S. Ma. Daily-aware personalized recommendation based on feature-level time series analysis. In WWW, pages 1373--1383, 2015. Google ScholarDigital Library
- H. Zhu, E. Chen, H. Xiong, K. Yu, H. Cao, and J. Tian. Mining mobile user preferences for personalized context-aware recommendation. TIST, 5(4):58, 2015. Google ScholarDigital Library
Index Terms
- Contextual Intent Tracking for Personal Assistants
Recommendations
Collaborative Nowcasting for Contextual Recommendation
WWW '16: Proceedings of the 25th International Conference on World Wide WebMobile digital assistants such as Microsoft Cortana and Google Now currently offer appealing proactive experiences to users, which aim to deliver the right information at the right time. To achieve this goal, it is crucial to precisely predict users' ...
Collaborative Intent Prediction with Real-Time Contextual Data
Special issue: Search, Mining and their Applications on Mobile DevicesIntelligent personal assistants on mobile devices such as Apple’s Siri and Microsoft Cortana are increasingly important. Instead of passively reacting to queries, they provide users with brand new proactive experiences that aim to offer the right ...
Deviation-Based Contextual SLIM Recommenders
CIKM '14: Proceedings of the 23rd ACM International Conference on Conference on Information and Knowledge ManagementContext-aware recommender systems (CARS) help improve the effectiveness of recommendations by adapting to users' preferences in different contextual situations. One approach to CARS that has been shown to be particularly effective is Context-Aware ...
Comments