Developing a Predictive Model of Quality of Experience for Internet Video

Improving users ’ quality of experience (QoE) is crucial for sus-taining the advertisement and subscription based revenue models that enable the growth of Internet video. Despite the rich litera-ture on video and QoE measurement, our understanding of Internet video QoE is limited because of the shift from traditional meth-ods of measuring video quality (e.g., Peak Signal-to-Noise Ratio) and user experience (e.g., opinion scores). These have been re-placed by new quality metrics (e.g., rate of buffering, bitrate) and new engagement-centric measures of user experience (e.g., view-ing time and number of visits). The goal of this paper is to develop a predictive model of Internet video QoE. To this end, we identify two key requirements for the QoE model: (1) it has to be tied in to observable user engagement and (2) it should be actionable to guide practical system design decisions. Achieving this goal is challeng-ing because the quality metrics are interdependent, they have com-plex and counter-intuitive relationships to engagement measures, and there are many external factors that confound the relationship between quality and engagement (e.g., type of video, user connec-tivity). To address these challenges, we present a data-driven ap-proach to model the metric interdependencies and their complex relationships to engagement, and propose a systematic framework to identify and account for the confounding factors. We show that a delivery infrastructure that uses our proposed model to choose CDN and bitrates can achieve more than 20 % improvement in over-all user engagement compared to strawman approaches