Abstract

Abstract: Mobile data off-loading can greatly decrease the load on and usage ofcurrent and future cellular data networks by exploiting opportunistic and frequent access to Wi-Fi connectivity. Unfortunately, Wi-Fi access from mobile devices canbe difficult during typical work commutes, e.g., via trains or cars on highways. Inthis paper, we propose a new approach: to preload the mobile device with contentthat a user might be interested in, and thereby avoid the need for cellular data access.We demonstrate the feasibility of this approach by developing a supervised machine learning model that learns from user preferences for different types of content, and propensity to be guided by the UI of the player, and predictively preload entire TV shows. Testing on a dataset of nearly 3.9 million sessions fromall over the UK to BBC TV shows, we find that predictive preloading can save over 71% of the mobile data for an average user.

Bio: Dmytro Karamshuk is a data scientists at King’s College London. His research interest is in machine learning approaches to modellingbehavior of online users. He has previously worked onstudying watching patterns of TV-streaming users (e.g.,BBC iPlayer), mining geo-location social networks (e.g.,Foursquare) and predicting user behaviour in imagebasedsocial platforms (e.g., Pinterest). Dmytro is a co-founder and a former CEO of Stanfy.com.