Statistical evaluation for quality of experience prediction based on quality of service parameters

Machine Learning (ML) provides a theoretical and methodological framework that allows to quantify the relationship between the user's Quality of Experience (OoE) and the network's Quality of Service (QoS). In the literature, several ML-based QoS/QoE correlation models have been proposed. All of those models use inductive supervised learning techniques and most of them are built in an offline batch manner using different ML methods such as: Least Squares Regression, Artificial Neural Netwcorks, Naive Bayes classifier, Support Vector Machines, k-Nearest Neighbors, Decision Trees, and Random Forest. This paper aims to evaluate these different ML methods and determine the most suitable one for the task of establishing the QoS/QoE correlation. The comparisons show that the Decision Trees and Random Forest models give the best results to this end.

I. Introduction

The number of Internet users has grown drastically in the last two decades. In 1995, there were only 16 million Internet users, which corresponds to 0.4 percent of the world's population [1]. By the end of 2015, this number exploded to reach 3.3 billion users, constituting 45% of the world's population [2]. This brisk growth is mainly due to the abundance of services available on the Internet such as search engines (e.g. Google, Bing, etc.), social media (e.g. Facebook, twitter, etc.), e-commerce (e.g. Amazon, e-bay, etc.) and multimedia services (e.g. IPTV, VoIP, VoD, etc.). These latter have become common and represent currently a very active research area and a new telecommunications market sector where customers are in a strong position. Indeed, the customers or end users have a variety of offers to select from. Apart from similar pricing schemes, which are a useful decision aid for users, their choices are also affected by the expected and experienced quality. Hence, the service providers are giving a lot of interest as to how users perceive usability, reliability, quality and price-worthiness. As a result, the concept of Quality of Experience (QoE) has been introduced in order to help the service providers to take into account the user's perception and satisfaction [3].