Data-driven modeling using machine learning (ML) holds great potential in many areas and can, for example, enable us to create more accurate models for Quality of Experience (QoE), which refers to the subjective quality of internet applications. However, such models are often black boxes, meaning we cannot directly understand how they work. In research, it is important for us to know which factors have the greatest impact on user satisfaction and what fundamental relationships are hidden within the data. This is where methods from explainable machine learning (eXplainable Artificial Intelligence, XAI) can help, and we have written a tutorial paper on how such methods can be applied to QoE modeling. The paper was published in the renowned journal IEEE Communications Surveys & Tutorials.

Link to paper:  A Tutorial on Data-Driven Quality of Experience Modeling With Explainable Artificial Intelligence