As the demand for over-the-top and online streaming services exponentially increases,\nmany techniques for Quality of Experience (QoE) provisioning have been studied. Users can take\nactions (e.g., skipping) while streaming a video. Therefore, we should consider the viewing pattern\nof users rather than the network condition or video quality. In this context, we propose a proactive\ncontent-loading algorithm for improving per-user personalized preferences using multinomial\nsoftmax classification. Based on experimental results, the proposed algorithm has a personalized\nper-user content waiting time that is significantly lower than that of competing algorithms.
Loading....