Predicting Quality of Experience from Performance Indicators : Modelling aggregated user survey responses based on telecommunications networks performance indicators

Abstract: As user experience can be a competitive edge, it lies in the interest of businesses to be aware of how users perceive the services they provide. For telecommunications operators, how network performance influences user experience is critical. To attain this knowledge, one can survey users. However, sometimes users are not available or willing to answer. For this reason, there exists an interest in estimating the quality of user experience without having to ask users directly. Previous research has studied how the relationship between network performance and the quality of experience can be modelled over time through a fixed window classification approach. This work aims to extend this research by investigating the applicability of a regression approach without the fixed window limitation by the application of an Long Short Term Memmory based Machine Learning model. Aggregation of both network elements and user feedback through the application of three different clustering techniques was used to overcome challenges in user feedback sparsity. The performance while using each clustering technique was evaluated. It was found that all three methods can outperform a baseline based on the weekly average of the user feedback. The effect of applying different levels of detrending was also examined. It was shown that detrending the time series based on a smaller superset may increase overall performance but hinder relative model improvement, indicating that some helpful information may be lost in this process. The results should inspire future works to consider a regression approach for modelling Quality of Experience as a function of network performance as an avenue worthy of further study. This work should also motivate further research into the generalizability of models trained on network elements that reside in areas of different urban and rural conditions.