Ofer Hadar

The increasing popularity of online video content and adaptive video streaming services, especially ones based on HTTP Adaptive Streaming, highlights the need for streaming optimization solutions. Predicting end users Quality of Experience (QoE) by using machine learning algorithms, may allow content servers to allocate bandwidth smartly and more efficiently. In this work, we present a new user quality of experience prediction algorithm which extracts features based on user traffic pattern parameters such as bit-rate, resolution, frame rate, etc. In order to optimize the features set and the corresponding machine learning algorithms, we have used three different feature selection algorithms and six different classifiers. We show that the Decision Tree algorithm achieved 86% accuracy in predicting the user quality of experience.