# Machine Learning-Driven Open-Source Framework for Assessing QoE in Multimedia Networks

arXiv: https://arxiv.org/abs/2406.08564 · HTML: https://mlsanity.com/paper/2406.08564/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 77 references that are in the map.
- First posted on arXiv 12 Jun 2024.

## Builds on (most cited first, 6 of 6)

- [QoE Management of Multimedia Streaming Services in Future Networks: A Tutorial and Survey](https://mlsanity.com/paper/1912.12467/) (2019)
- [Convolutional Neural Networks for Continuous QoE Prediction in Video Streaming Services](https://mlsanity.com/paper/2003.08574/) (2020)
- [Supervised Learning based QoE Prediction of Video Streaming in Future Networks: A Tutorial with Comparative Study](https://mlsanity.com/paper/2202.02454/) (2022)
- [Enhancing Quality of Experience in Telecommunication Networks: A Review of Frameworks and Machine Learning Algorithms](https://mlsanity.com/paper/2404.16787/) (2024)
- [YouTube QoE Evaluation Tool for Android Wireless Terminals](https://mlsanity.com/paper/1405.4709/) (2014)
- [Design and Implementation of Fragmented Clouds for Evaluation of Distributed Databases](https://mlsanity.com/paper/2209.09487/) (2022)

## Built on by (most cited first, 1 of 1)

- [Bridging Subjective and Objective QoE: Operator-Level Aggregation Using LLM-Based Comment Analysis and Network MOS Comparison](https://mlsanity.com/paper/2506.00924/) (2025)

## Abstract (arXiv)

The Internet is integral to modern life, influencing communication, business, and lifestyles globally. As dependence on Internet services grows, the demand for high-quality service delivery increases. Service providers must maintain high standards of quality of service and quality of experience (QoE) to ensure user satisfaction. QoE, which reflects user satisfaction with service quality, is a key metric for multimedia services, yet it is challenging to measure due to its subjective nature and the complexities of real-time feedback. This paper introduces a machine learning-based framework for objectively assessing QoE in multimedia networks. The open-source framework complies with the ITU-T P.1203 standard. It automates data collection and user satisfaction prediction using key network parameters such as delay, jitter, packet loss, bitrate, and throughput. Using a dataset of over 20,000 records from various network conditions, the Random Forest model predicts the mean opinion score with 95.8% accuracy. Our framework addresses the limitations of existing QoE models by integrating real-time data collection, machine learning predictions, and adherence to international standards. This approach enhances QoE evaluation accuracy and allows dynamic network resource management, optimizing performance and cost-efficiency. Its open-source nature encourages adaptation and extension for various multimedia services. The findings significantly affect the telecommunications industry in managing and optimizing multimedia services. The network centric QoE prediction of the framework offers a scalable solution to improve user satisfaction without the need for content-specific data. Future enhancements could include advanced machine learning models and broader applicability to digital services. This research contributes a practical, standardized tool for QoE assessment across diverse networks and platforms.