Smartphone App Usage Prediction Using Points of Interest

Donghan Yu, Yong Li, Fengli Xu, Pengyu Zhang, Vassilis Kostakos
2018 Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies  
In this paper we present the first population-level, city-scale analysis of application usage on smartphones. Using deep packet inspection at the network operator level, we obtained a geo-tagged dataset with more than 6 million unique devices that launched more than 10,000 unique applications across the city of Shanghai over one week. We develop a technique that leverages transfer learning to predict which applications are most popular and estimate the whole usage distribution based on the
more » ... of Interest (POI) information of that particular location. We demonstrate that our technique has an 83.0% hitrate in successfully identifying the top five popular applications, and a 0.15 RMSE when estimating usage with just 10% sampled sparse data. It outperforms by about 25.7% over the existing state-of-the-art approaches. Our findings pave the way for predicting which apps are relevant to a user given their current location, and which applications are popular where. The implications of our findings are broad: it enables a range of systems to benefit from such timely predictions, including operating systems, network operators, appstores, advertisers, and service providers. We present the first population-level, city-scale analysis of application usage on smartphones. Our work contributes to the growing body of research that has been spurred by the flourishing appstore economy, and which has motivated researchers in recent years to investigate users' smartphone application usage behaviour. For example, previous works have looked at how individuals download, install, and use different applications on their personal devices [1-3]. Typically, these works investigate behaviour at an individual level, and often attempt to cluster users based on similarities of their behaviours [4] . As such, most studies only have sampled information about application usage, either collected from the mobile devices of volunteers or monitored on the network side with low penetration. Despite the ubiquity and mobility of smartphones and personal devices, very little works to date have investigated how context, and in particular physical location, affects application usage. For example, some prior works
doi:10.1145/3161413 fatcat:6bofzlhfsnfhrp7ag5ulmdabwe