Personalized QoE Prediction: A Demographic-Augmented Machine Learning Framework for 5G Video Streaming Networks

TL;DR

This paper introduces a demographic-aware machine learning framework that significantly improves personalized QoE prediction accuracy in 5G video streaming by augmenting datasets with user demographic data.

Contribution

It proposes a novel demographic-based data augmentation strategy and evaluates various ML models, demonstrating enhanced prediction accuracy for personalized QoE in 5G networks.

Findings

Demographic augmentation expands dataset sixfold.

TabNet outperforms other models in prediction accuracy.

Personalized QoE prediction becomes more robust with demographic data.

Abstract

Quality of Experience (QoE) prediction is a critical component of modern multimedia systems, particularly for adaptive video streaming in 5G networks. Accurate QoE estimation enables intelligent resource management and supports user centric service delivery. Existing QoE prediction approaches primarily rely on limited datasets and assume uniform user perception, which restricts their applicability in heterogeneous real world environments. This paper proposes a demographic aware machine learning framework for personalized QoE prediction. We introduce a behaviorally realistic demographic based data augmentation strategy that expands a small QoE dataset six fold by modeling varying user sensitivities to streaming impairments such as rebuffering, bitrate variation, and quality degradation. Using the augmented dataset, we evaluate a comprehensive set of classical machine learning models alongside advanced deep learning architectures, including an attention-based MLP and TabNet. Experimental results demonstrate significant improvements in prediction accuracy across RMSE, MAE, and R metrics compared to baseline models. Among all evaluated approaches, TabNet achieves the strongest performance, benefiting from its inherent feature selection and attention mechanisms. The results confirm that demographic-aware augmentation substantially enhances QoE prediction robustness and provides a scalable direction for personalized QoE-aware intelligence in 5G video streaming networks.