Profiling users in a 3g network using hourglass co-clustering

Abstract

With widespread popularity of smart phones, more and more users are accessing the Internet on the go. Understanding mobile user browsing behavior is of great significance for several reasons. For example, it can help cellular (data) service providers (CSPs) to improve service performance, thus increasing user satisfaction. It can also provide valuable insights about how to enhance mobile user experience by providing dynamic content personalization and recommendation, or location-aware services.In this paper, we try to understand mobile user browsing behavior by investigating whether there exists distinct "behavior patterns" among mobile users. Our study is based on real mobile network data collected from a large 3G CSP in North America. We formulate this user behavior profiling problem as a co-clustering problem, i.e., we group both users (who share similar browsing behavior), and browsing profiles (of like-minded users) simultaneously. We propose and develop a scalable co-clustering methodology, Phantom, using a novel hourglass model. The proposed hourglass model first reduces the dimensions of the input data and performs divisive hierarchical co-clustering on the lower dimensional data; it then carries out an expansion step that restores the original dimensions. Applying Phantom to the mobile network data, we find that there exists a number of prevalent and distinct behavior patterns that persist over time, suggesting that user browsing behavior in 3G cellular networks can be captured using a small number of co-clusters. For instance, behavior of most users can be classified as either homogeneous (users with very limited set of browsing interests) or heterogeneous (users with very diverse browsing interests), and such behavior profiles do not change significantly at either short (30-min) or long (6 hour) time scales.

Cellular data network infrastructure characterization and implication on mobile content placement

“…Efforts on reverse engineering properties of the Internet [32] have been shown to be quite successful; however, very little work has been done in the space of cellular IP networks. Complementary to our study, the most recent work by Keralapura et al profiled the browsing behavior by investigating whether there exists distinct behavior pattern among mobile users [20]. Their study implemented effective co-clustering on large scale user-level web browsing traces collected from one cellular provider.…”

Understanding Mobile Traffic Patterns of Large Scale Cellular Towers in Urban Environment

“…And Zhang et al [26] tried to understand the characteristics of cellular data traffic by comparing it to wireline data traffic. Other studies combine the CDR, GPS locations, and application traces to investigate the land usage [24,20], social interactions [7], location-based patterns [5], and web and data access patterns [13,12]. In this paper, we focus on investigating the mobile data traffic patterns from different domains, including time, location and frequency, which provides a comprehensive understanding of the traffic patterns of large scale cellular towers with a simple but deep model that is able to characterize the city geographical features and human communication regularity.…”

A Sharing- and Competition-Aware Framework for Cellular Network Evolution Planning

“…Other works use traffic demand, either concentrating on profiling the users [25], [26], [27], or focusing more on the network behaviour [8], [27], [28], [29] but none of them investigates long term planning decisions. The work in [8] is of interest to us because it has an objective orthogonal to ours; it is focused on energy savings and green networking and envisions dynamically switching off base stations at off-peak times in different parts of the topology.…”