Preference, context and communities

• DOI: 10.1145/2493988.2494333
• Publication Date: 2013-09-11T06:54:53Z
• Authors: Ye Xu; Mu Lin; Hong Lu; Giuseppe Cardone; Nicholas Lane; Zhenyu Chen; Andrew Campbell; Tanzeem Choudhury
• Keywords: Smartphone app; Smartphone application; Mobile apps; App store

Reliable smartphone app prediction can strongly benefit both users and phone system performance alike. However, real-world usage behavior is a complex phenomena driven by number of competing factors. In this pa- per, we develop an model that leverages three key everyday factors affect decisions -- (1) intrinsic user preferences historical patterns; (2) activities the environment as observed through sensor-based contextual signals; and, (3) shared aggregate patterns appear in various communities. While rapid progress has been made recently prediction, existing models tend to focus on only one these We evaluate multi-faceted approach using 3-week 35-user field trial, along with analysis logs 4,606 worldwide. find our not produce more robust predictions than conventional techniques, but it also enable significant optimizations.