Abstract
Intelligent 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 information at the right time. It is, therefore, crucial for personal assistants to understand users’ intent, that is, what information users need now. Intent is closely related to context. Various contextual signals, including spatio-temporal information and users’ activities, can signify users’ intent. It is, however, challenging to model the correlation between intent and context. Intent and context are highly dynamic and often sequentially correlated. Contextual signals are usually sparse, heterogeneous, and not simultaneously available. We propose an innovative collaborative nowcasting model to jointly address all these issues. The model effectively addresses the complex sequential and concurring correlation between context and intent and recognizes users’ real-time intent with continuously arrived contextual signals. We extensively evaluate the proposed model with real-world data sets from a commercial personal assistant. The results validate the effectiveness the proposed model, and demonstrate its capability of handling the real-time flow of contextual signals. The studied problem and model also provide inspiring implications for new paradigms of recommendation on mobile intelligent devices.
- Gediminas Adomavicius and Alexander Tuzhilin. 2011. Context-aware recommender systems. In Recommender Systems Handbook. Springer, 217--253.Google Scholar
- Jushan Bai. 2003. Inferential theory for factor models of large dimensions. Econometrica 71, 1 (2003), 135--171.Google ScholarCross Ref
- Jushan Bai and Peng Wang. 2016. Econometric analysis of large factor models. Annu. Rev. Econ. 8, 1 (2016), 53--80.Google Scholar
- Marta Banbura, Domenico Giannone, Michele Modugno, and Lucrezia Reichlin. 2013. Now-casting and the real-time data flow. Handbook of Economic Forecasting (2013).Google Scholar
- Marta Banbura, Domenico Giannone, and Lucrezia Reichlin. 2012. Nowcasting. The Oxford Handbook of Economic Forecasting (2012).Google Scholar
- Rasmus Bro. 1997. PARAFAC. Tutorial and applications. Chemomet. Intell. Lab. Syst. 38, 2 (1997), 149--171.Google ScholarCross Ref
- Laurent Charlin, Rajesh Ranganath, James McInerney, and David M. Blei. 2015. Dynamic poisson factorization. In RecSys’15. 155--162. Google ScholarDigital Library
- Peter A. Chew, Brett W. Bader, Tamara G. Kolda, and Ahmed Abdelali. 2007. Cross-language information retrieval using PARAFAC2. In KDD’07. 143--152. Google ScholarDigital Library
- Aaron Clauset, Cosma Rohilla Shalizi, and M. E. J. Newman. 2009. Power-law distributions in empirical data. SIAM Rev. 51, 4 (2009), 661--703. Google ScholarDigital Library
- Michael Dixon and Gerry Wiener. 1993. TITAN: Thunderstorm identification, tracking, analysis, and nowcasting-A radar-based methodology. J. Atmos. Ocean. Technol. 10, 6 (1993), 785--797.Google ScholarCross Ref
- Catherine Doz, Domenico Giannone, and Lucrezia Reichlin. 2011. A two-step estimator for large approximate dynamic factor models based on Kalman filtering. J. Econ. 164, 1 (2011), 188--205.Google ScholarCross Ref
- Catherine Doz, Domenico Giannone, and Lucrezia Reichlin. 2012. A quasi--maximum likelihood approach for large, approximate dynamic factor models. Rev. Econ. Stat. 94, 4 (2012), 1014--1024.Google ScholarCross Ref
- Brendan Duncan and Charles Elkan. 2014. Nowcasting with numerous candidate predictors. In ECML PKDD’14. 370--385.Google Scholar
- Mario Forni, Domenico Giannone, Marco Lippi, and Lucrezia Reichlin. 2009. Opening the black box: Structural factor models with large cross sections. Econ. Theory 25, 05 (2009), 1319--1347.Google ScholarCross Ref
- Domenico Giannone, Lucrezia Reichlin, and Luca Sala. 2005. Monetary policy in real time. In NBER Macroeconomics Annual 2004, Volume 19. 161--224.Google ScholarCross Ref
- Domenico Giannone, Lucrezia Reichlin, and David Small. 2008. Nowcasting: The real-time informational content of macroeconomic data. J. Mon. Econ. 55, 4 (2008), 665--676.Google ScholarCross Ref
- Richard A. Harshman. 1972. PARAFAC2: Mathematical and technical notes. UCLA Work. Pap. Phonet. 22, 3044 (1972), 122215.Google Scholar
- Thomas Hofmann. 2003. Collaborative filtering via gaussian probabilistic latent semantic analysis. In SIGIR’03. 259--266. Google ScholarDigital Library
- Dietmar Jannach, Lukas Lerche, and Michael Jugovac. 2015. Adaptation and evaluation of recommendations for short-term shopping goals. In RecSys’15. 211--218. Google ScholarDigital Library
- Rudolph Emil Kalman. 1960. A new approach to linear filtering and prediction problems. J. Basic Eng. 82, 1 (1960), 35--45.Google ScholarCross Ref
- Alexandros Karatzoglou, Xavier Amatriain, Linas Baltrunas, and Nuria Oliver. 2010. Multiverse recommendation: N-dimensional tensor factorization for context-aware collaborative filtering. In RecSys’10. 79--86. Google ScholarDigital Library
- Henk AL Kiers, Jos MF Ten Berge, and Rasmus Bro. 1999. PARAFAC2-Part I. A direct fitting algorithm for the PARAFAC2 model. J. Chemomet. 13, 3--4 (1999), 275--294.Google ScholarCross Ref
- Tamara G. Kolda and Brett W. Bader. 2009. Tensor decompositions and applications. SIAM Rev. 51, 3 (2009), 455--500. Google ScholarDigital Library
- Yehuda Koren. 2009. Collaborative filtering with temporal dynamics. In KDD’09. 447--456. Google ScholarDigital Library
- Yehuda Koren and Robert Bell. 2011. Advances in collaborative filtering. In Recommender Systems Handbook. 145--186.Google Scholar
- Vasileios Lampos and Nello Cristianini. 2012. Nowcasting events from the social web with statistical learning. Trans. Iintell. Syst. Technol. 3, 4 (2012), 72. Google ScholarDigital Library
- Thomas Lansdall-Welfare, Vasileios Lampos, and Nello Cristianini. 2012. Nowcasting the mood of the nation. Significance 9, 4 (2012), 26--28.Google ScholarCross Ref
- D. N. Lawley and A. E. Maxwell. 1962. Factor analysis as a statistical method. J. Roy. Stat. Soc. D 12, 3 (1962), 209--229.Google Scholar
- Lei Lin, Ming Ni, Qing He, Jing Gao, Adel W. Sadek, and Transportation Informatics Tier I. Director. 2015. Modeling the impacts of inclement weather on freeway traffic speed: An exploratory study utilizing social media data. In Proceedings of the Transportation Research Board 94th Annual Meeting.Google ScholarCross Ref
- Qi Liu, Haiping Ma, Enhong Chen, and Hui Xiong. 2013. A survey of context-aware mobile recommendations. Int. J. Inf. Technol. Dec. Mak. 12, 01 (2013), 139--172.Google Scholar
- Alexander E. MacDonald, Yuanfu Xie, and Randolph H. Ware. 2002. Diagnosis of three-dimensional water vapor using a GPS network. Mon. Weather Rev. 130, 2 (2002), 386--397.Google ScholarCross Ref
- Tariq Mahmood, Francesco Ricci, and Adriano Venturini. 2009. Improving recommendation effectiveness: Adapting a dialogue strategy in online travel planning. Inf. Technol. Tour. 11, 4 (2009), 285--302.Google ScholarCross Ref
- Clifford Mass. 2012. Nowcasting: The promise of new technologies of communication, modeling, and observation. Bull. Am. Meteorol. Soc. 93, 6 (2012), 797--809.Google ScholarCross Ref
- William R. Moninger, Stanley G. Benjamin, Brian D. Jamison, Thomas W. Schlatter, Tracy Lorraine Smith, and Edward J. Szoke. 2010. Evaluation of regional aircraft observations using TAMDAR. Weather Forecast. 25, 2 (2010), 627--645.Google ScholarCross Ref
- Stephen W. Raudenbush and Anthony S. Bryk. 2002. Hierarchical Linear Models: Applications and Data Analysis Methods. Sage.Google Scholar
- Steffen Rendle. 2012. Factorization machines with libFM. Trans. Intell. Syst. Technol. 3, 3 (2012), 1--22. Google ScholarDigital Library
- Steffen Rendle, Christoph Freudenthaler, and Lars Schmidt-Thieme. 2010. Factorizing personalized markov chains for next-basket recommendation. In WWW’10. 811--820. Google ScholarDigital Library
- Steven L. Scott and Hal R. Varian. 2014. Predicting the present with bayesian structural time series. Int. J. Math. Model. Numer. Optim. 5, 1--2 (2014), 4--23.Google Scholar
- Mary Beth Seasholtz and Bruce Kowalski. 1993. The parsimony principle applied to multivariate calibration. Anal. Chim. Acta 277, 2 (1993), 165--177.Google ScholarCross Ref
- Milad Shokouhi and Qi Guo. 2015. From queries to cards: Re-ranking proactive card recommendations based on reactive search history. In SIGIR’15. 695--704. Google ScholarDigital Library
- Yang Song and Qi Guo. 2016. Query-less: Predicting task repetition for NextGen proactive search and recommendation engines. In WWW’16. 543--553. Google ScholarDigital Library
- James H. Stock and Mark W. Watson. 2002. Forecasting using principal components from a large number of predictors. J. Am. Stat. Assoc. 97, 460 (2002), 1167--1179.Google ScholarCross Ref
- John Z. Sun, Dhruv Parthasarathy, and Kush R. Varshney. 2014. Collaborative kalman filtering for dynamic matrix factorization. Trans. Sign. Process. 62, 14 (2014), 3499--3509. Google ScholarDigital Library
- Yu Sun, Nicholas Jing Yuan, Yingzi Wang, Xing Xie, Kieran McDonald, and Rui Zhang. 2016a. Contextual intent tracking for personal assistants. In KDD’16. 273--282. Google ScholarDigital Library
- Yu Sun, Nicholas Jing Yuan, Xing Xie, Kieran McDonald, and Rui Zhang. 2016b. Collaborative nowcasting for contextual recommendation. In WWW’16. 1407--1418. Google ScholarDigital Library
- Yingzi Wang, Nicholas Jing Yuan, Yu Sun, Fuzheng Zhang, Xing Xie, Qi Liu, and Enhong Chen. 2016. A contextual collaborative approach for app usage forecasting. In UbiComp’16. 1247--1258. Google ScholarDigital Library
- Greg Welch and Gary Bishop. 1995. An Introduction to the Kalman Filter. Technical Report. Chapel Hill, NC. Google ScholarDigital Library
- James W. Wilson, N. Andrew Crook, Cynthia K. Mueller, Juanzhen Sun, and Michael Dixon. 1998. Nowcasting thunderstorms: A status report. Bull. Am. Meteorol. Soc. 79, 10 (1998), 2079--2099.Google ScholarCross Ref
- Qiang Wu, Christopher J. C. Burges, Krysta M. Svore, and Jianfeng Gao. 2010. Adapting boosting for information retrieval measures. Inf. Retriev. 13, 3 (2010), 254--270. Google ScholarDigital Library
- Yongfeng Zhang, Min Zhang, Yi Zhang, Guokun Lai, Yiqun Liu, Honghui Zhang, and Shaoping Ma. 2015. Daily-aware personalized recommendation based on feature-level time series analysis. In WWW’15. 1373--1383. Google ScholarDigital Library
- Hengshu Zhu, Enhong Chen, Hui Xiong, Kuifei Yu, Huanhuan Cao, and Jilei Tian. 2015. Mining mobile user preferences for personalized context-aware recommendation. Trans. Intell. Syst. Technol. 5, 4 (2015), 58. Google ScholarDigital Library
Index Terms
- Collaborative Intent Prediction with Real-Time Contextual Data
Recommendations
Contextual Intent Tracking for Personal Assistants
KDD '16: Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data MiningA 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 ...
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' ...
A ubiquitous, semantic based virtual shared environment for collaborative virtual work groups
Collaborative Virtual Work Groups (CVWG) are small groups of people that work together but are distanced geographically, temporarily or organisationally, keeping their connections through technologies like groupware. Groupware enables a shared ...
Comments