Predicting Replacement of Smartphones with Mobile App Usage

详细信息    查看全文

• 关键词：App usage ; Smartphone replacement ; Hazard model ; Mobile log data
• 刊名：Lecture Notes in Computer Science
• 出版年：2016
• 出版时间：2016
• 年：2016
• 卷：10041
• 期：1
• 页码：343-351
• 全文大小：469 KB
• 参考文献：1.Böhmer, M., Hecht, B., et al.: Falling asleep with angry birds, Facebook and kindle: a large scale study on mobile application usage. In: MobileHCI, pp. 47–56 (2011)
  2.Böhning, D.: Multinomial logistic regression algorithm. Ann. Inst. Stat. Math. 44(1), 197–200 (1992)CrossRef MATH
  3.Buckinx, W., Van den Poel, D.: Customer base analysis: partial defection of behaviourally loyal clients in a non-contractual FMCG retail setting. EJOR 164(1), 252–268 (2005)CrossRef MATH
  4.Cox, D.R.: Regression models and life-tables. In: Kotz, S., Johnson, N.L. (eds.) Breakthroughs in Statistics. Springer, New York (1992)
  5.Do, T.M.T., Gatica-Perez, D.: By their apps you shall understand them: mining large-scale patterns of mobile phone usage. In: MUM (2010)
  6.Ghose, A., Han, S.P.: An empirical analysis of user content generation and usage behavior on the mobile internet. Manag. Sci. 57(9), 1671–1691 (2011)CrossRef
  7.Kapoor, K., Sun, M., Srivastava, J., Ye, T.: A hazard based approach to user return time prediction. In: KDD, pp. 1719–1728 (2014)
  8.Parate, A., Böhmer, M., Chu, D., et al.: Practical prediction and prefetch for faster access to applications on mobile phones. In: UbiComp, pp. 275–284 (2013)
  9.Shi, Y., Karatzoglou, A., Baltrunas, L., Larson et al.: TFMAP: optimizing map for top-n context-aware recommendation. In: SIGIR, pp. 155–164 (2012)
  10.Shin, C., Hong, J.H., Dey, A.K.: Understanding and prediction of mobile application usage for smart phones. In: UbiComp, pp. 173–182 (2012)
  11.Xie, Y., Li, X., Ngai, E., Ying, W.: Customer churn prediction using improved balanced random forests. Expert Syst. Appl. 36(3), 5445–5449 (2009)CrossRef
  12.Yang, J., Wei, X., et al.: Activity lifespan: an analysis of user survival patterns in online knowledge sharing communities. ICWSM 10, 186–193 (2010)
  13.Yuan, B., Xu, B., Chung, T., Shuai, K., Liu, Y.: Mobile phone recommendation based on phone interest. In: Benatallah, B., Bestavros, A., Manolopoulos, Y., Vakali, A., Zhang, Y. (eds.) WISE 2014. LNCS, vol. 8786, pp. 308–323. Springer, Heidelberg (2014). doi:10.​1007/​978-3-319-11749-2_​24
  14.Zhu, H., Chen, E., Xiong, H., Cao, H., Tian, J.: Mobile app. classification with enriched contextual information. IEEE Trans. Mob. Comput. 13(7), 1550–1563 (2014)CrossRef
  
• 作者单位：Dun Yang (19)
  Zhiang Wu (19)
  Xiaopeng Wang (20)
  Jie Cao (19)
  Guandong Xu (21)
  
  19. School of Info. Engineering, Nanjing University of Finance and Economics, Nanjing, China
  20. Jiangsu Posts & Telecommunications Planning and Designing Institute, Nanjing, China
  21. Advanced Analytics Institute, University of Technology, Sydney, Australia
  
• 丛书名：Web Information Systems Engineering ¨C WISE 2016
• ISBN：978-3-319-48740-3
• 刊物类别：Computer Science
• 刊物主题：Artificial Intelligence and Robotics
  Computer Communication Networks
  Software Engineering
  Data Encryption
  Database Management
  Computation by Abstract Devices
  Algorithm Analysis and Problem Complexity
  
• 出版者：Springer Berlin / Heidelberg
• ISSN：1611-3349
• 卷排序：10041

文摘

To identify right customers who intend to replace the smartphone can help to perform precision marketing and thus bring significant financial gains to cellphone retailers. In this paper, we provide a study of exploiting mobile app usage for predicting users who will change the phone in the future. We first analyze the characteristics of mobile log data and develop the temporal bag-of-apps model, which can transform the raw data to the app usage vectors. We then formularize the prediction problem, present the hazard based prediction model, and derive the inference procedure. Finally, we evaluate both data model and prediction model on real-world data. The experimental results show that the temporal usage data model can effectively capture the unique characteristics of mobile log data, and the hazard based prediction model is thus much more effective than traditional classification methods. Furthermore, the hazard model is explainable, that is, it can easily show how the replacement of smartphones relate to mobile app usage over time.