ABSTRACT
Reliable smartphone app prediction can strongly benefit both users and phone system performance alike. However, real-world smartphone app usage behavior is a complex phenomena driven by a number of competing factors. In this pa- per, we develop an app usage prediction model that leverages three key everyday factors that affect app usage decisions -- (1) intrinsic user app preferences and user historical patterns; (2) user activities and the environment as observed through sensor-based contextual signals; and, (3) the shared aggregate patterns of app behavior that appear in various user communities. While rapid progress has been made recently in smartphone app prediction, existing prediction models tend to focus on only one of these factors. We evaluate a multi-faceted approach to prediction using (1) a 3-week 35-user field trial, along with (2) analysis of app usage logs of 4,606 smartphone users worldwide. We find our app usage model can not only produce more robust app predictions than conventional techniques, but it can also enable significant smartphone system optimizations.
- MTA Subway Time. http://apps.mta.info/traintime/.Google Scholar
- Runkeeper. http://runkeeper.com/.Google Scholar
- R. Bridle and E. McCreath., Predictive Menu Selection on a Mobile Phone, In ECML'05. pp.75--88, 2005Google Scholar
- C. Shin, J.-H. Hong, A. Dey., Understanding and Prediction of Mobile Application Usage for Smart Phones, In Ubicomp'12. pp.173--182, 2012. Google ScholarDigital Library
- 5. C. Yoon, et al., AppScope: Application Energy Metering Framework for Android Smartphone Using Kernel Activity Monitoring, In ATC'12. pp.1--14, 2012. Google ScholarDigital Library
- T. Yan et al., Fast App Launching for Mobile Devices using Predictive User Context, In MobiSys'12. pp.113--126, 2012. Google ScholarDigital Library
- K. Shi and K. Ali., GetJar mobile application recommendations with very sparse datasets, In KDD'12. pp.204--212, 2012. Google ScholarDigital Library
- D. Peebles, et al., Community-guided learning: Exploiting mobile sensor users to model human behavior, In AAAI'10. pp.1600--1606, 2010.Google Scholar
- H. Lu et al., The Jigsaw continuous sensing engine for mobile phone applications, In Sensys'10. pp.71--84, 2010. Google ScholarDigital Library
- B. Yan and G. Chen., AppJoy: personalized mobile application discovery, In MobiSys'11. pp.113--126, 2011. Google ScholarDigital Library
- J. Shawe-Taylor and N. Cristianini., Kernel Methods for Pattern Analysis, Cambridge Press, 2004. Google ScholarDigital Library
- W. Ping, et al., FAMER: Making Multi-Instance Learning Better and Faster, In SDM'11. pp. 594--605, 2011.Google ScholarCross Ref
- Y. Xu, et al., Multi-instance Metric Learning, In ICDM'11. pp.874--883, 2011. Google ScholarDigital Library
- S. Lyu., Mercer kernels for object recognition with local features, In CVPR'05. pp.223--229, 2005. Google ScholarDigital Library
- J. T. Kwok and P.-M. Cheung., Marginalized multi-instance kernels, In IJCAI'07. pp.901--906, 2007. Google ScholarDigital Library
- J. Shao., Mathematical statistics, New York Springer-Verlag, 1998.Google Scholar
- C. M. Bishop., Pattern Recognition and Machine Learning, Springer, 2006. Google ScholarDigital Library
- W. Pan, N. Aharony and A. Pentland., Composite Social Network for Predicting Mobile Apps Installation, In AAAI'11. pp.821--827, 2007.Google Scholar
- H. Verkasalo., Contextual patterns in mobile service usage, PUC, 13(5):331--342, 2009. Google ScholarDigital Library
- A. Woznica and A. Kalousis., Adaptive distances on sets of vectors, In ICDM'10. pp.579--588, 2010. Google ScholarDigital Library
- B. Matthias et al., Falling asleep with Angry Birds, Facebook and Kindle: a large scale study on mobile application usage, In MobileHCI'11. pp.47--56, 2011. Google ScholarDigital Library
- R. Ahmad et al., Exploring iPhone usage: the influence of socioeconomic differences on smartphone adoption, usage and usability, In MobileHCI'12. pp.11--20, 2012. Google ScholarDigital Library
- T. Minh et al., Smartphone usage in the wild: a large-scale analysis of applications and context. In ICMI'11. pp.353--360, 2011. Google ScholarDigital Library
- O. Franko and T. Tirrell., Smartphone app use among medical providers in ACGME training programs. Journal of Medical Systems, 36: pp.3135--3139, 2011. Google ScholarDigital Library
- J. S. Breese, D. Heckerman, and C. Kadie., Empirical analysis of predictive algorithms for collaborative filtering, In UAI'98. pp.43--52, 1998. Google ScholarDigital Library
- J. L. Herlocker et al., Evaluating collaborative filtering recommender systems. ACM Trans. Inf. Syst., 22(1):pp.5--53, 2004. Google ScholarDigital Library
- A. Popescul, D. M. Pennock, and S. Lawrence., Probabilistic models for unified collaborative and content-based recommendation in sparse-data environments, In UAI'01. pp.437--444, 2001. Google ScholarDigital Library
- N. Lane et al., Enabling large-scale human activity inference on smartphones using community similarity networks, In UbiComp'11. pp.355--364, 2011. Google ScholarDigital Library
- N. Lane et al., Exploiting social networks for large-scale human behavior modeling, IEEE Pervasive Computing, 10(4):pp.45--53, 2011. Google ScholarDigital Library
Index Terms
- Preference, context and communities: a multi-faceted approach to predicting smartphone app usage patterns
Recommendations
Understanding and prediction of mobile application usage for smart phones
UbiComp '12: Proceedings of the 2012 ACM Conference on Ubiquitous ComputingIt is becoming harder to find an app on one's smart phone due to the increasing number of apps available and installed on smart phones today. We collect sensory data including app use from smart phones, to perform a comprehensive analysis of the context ...
Improving Application Launch Performance in Smartphones Using Recurrent Neural Network
ICMLT '18: Proceedings of the 2018 International Conference on Machine Learning TechnologiesMobile phones became indispensable tools in our lives, with Android being the most used mobile OS. These devices depend on managing application lifecycles to improve launch performance, but the management of application processes is not done in an ...
Prophet: what app you wish to use next
UbiComp '13 Adjunct: Proceedings of the 2013 ACM conference on Pervasive and ubiquitous computing adjunct publicationA variety of applications (app) installed on smart phones do greatly enrich our lives, but make it more difficult to organize our screens and folders. Predicting apps that will be in use next can benefit users a lot. In this poster, we propose some ...
Comments