On the Feature Discovery for App Usage Prediction in Smartphones

With the increasing number of mobile Apps developed, they are now closely integrated into daily life. In this paper, we develop a framework to predict mobile Apps that are most likely to be used regarding the current device status of a smartphone. Such an Apps usage prediction framework is a crucial prerequisite for fast App launching, intelligent user experience, and power management of smartphones. By analyzing real App usage log data, we discover two kinds of features: The Explicit Feature (EF) from sensing readings of built-in sensors, and the Implicit Feature (IF) from App usage relations. The IF feature is derived by constructing the proposed App Usage Graph (abbreviated as AUG) that models App usage transitions. In light of AUG, we are able to discover usage relations among Apps. Since users may have different usage behaviors on their smartphones, we further propose one personalized feature selection algorithm. We explore minimum description length (MDL) from the training data and select those features which need less length to describe the training data. The personalized feature selection can successfully reduce the log size and the prediction time. Finally, we adopt the kNN classification model to predict Apps usage. Note that through the features selected by the proposed personalized feature selection algorithm, we only need to keep these features, which in turn reduces the prediction time and avoids the curse of dimensionality when using the kNN classifier. The results based on a real dataset demonstrate the effectiveness of the proposed framework and show the predictive capability for App usage prediction.

[1]  Jie Liu,et al.  Fast app launching for mobile devices using predictive user context , 2012, MobiSys '12.

[2]  Naranker Dulay,et al.  Predicting human behaviour from selected mobile phone data points , 2010, UbiComp.

[3]  Philip S. Yu,et al.  Mining Usage Traces of Mobile Apps for Dynamic Preference Prediction , 2013, PAKDD.

[4]  Jon M. Kleinberg,et al.  The link-prediction problem for social networks , 2007, J. Assoc. Inf. Sci. Technol..

[5]  Daniel Gatica-Perez,et al.  Smartphone usage in the wild: a large-scale analysis of applications and context , 2011, ICMI '11.

[6]  Jorma Rissanen,et al.  Hypothesis Selection and Testing by the MDL Principle , 1999, Comput. J..

[7]  Wang-Chien Lee,et al.  A Framework for Personal Mobile Commerce Pattern Mining and Prediction , 2012, IEEE Transactions on Knowledge and Data Engineering.

[8]  Hiroyuki Yokoyama,et al.  Operation Prediction for Context-Aware User Interfaces of Mobile Phones , 2009, 2009 Ninth Annual International Symposium on Applications and the Internet.

[9]  Wen-Chih Peng,et al.  Mining Temporal Profiles of Mobile Applications for Usage Prediction , 2012, 2012 IEEE 12th International Conference on Data Mining Workshops.

[10]  Jin-Hyuk Hong,et al.  Understanding and prediction of mobile application usage for smart phones , 2012, UbiComp.

[11]  Wang-Chien Lee,et al.  App recommendation: a contest between satisfaction and temptation , 2013, WSDM.

[12]  Kamal Ali,et al.  GetJar mobile application recommendations with very sparse datasets , 2012, KDD.

[13]  Cecilia Mascolo,et al.  NextPlace: A Spatio-temporal Prediction Framework for Pervasive Systems , 2011, Pervasive.

[14]  J. Rissanen,et al.  Modeling By Shortest Data Description* , 1978, Autom..

[15]  Nitesh V. Chawla,et al.  Link Prediction and Recommendation across Heterogeneous Social Networks , 2012, 2012 IEEE 12th International Conference on Data Mining.

[16]  Jaana Kekäläinen,et al.  Cumulated gain-based evaluation of IR techniques , 2002, TOIS.

[17]  Guanling Chen,et al.  AppJoy: personalized mobile application discovery , 2011, MobiSys '11.

[18]  Licia Capra,et al.  Temporal diversity in recommender systems , 2010, SIGIR.

[19]  Anna Monreale,et al.  WhereNext: a location predictor on trajectory pattern mining , 2009, KDD.

[20]  M. Matsumoto,et al.  Proposition of the context-aware interface for cellular phone operations , 2008, 2008 5th International Conference on Networked Sensing Systems.

[21]  Thorsten Joachims,et al.  Playlist prediction via metric embedding , 2012, KDD.

[22]  Jacob Kogan,et al.  Feature Selection over Distributed Data Streams through Convex Optimization , 2012, SDM.

[23]  Wen-Chih Peng,et al.  Exploring Spatial-Temporal Trajectory Model for Location Prediction , 2011, 2011 IEEE 12th International Conference on Mobile Data Management.