Saved in:
Bibliographic Details
Main Authors: Singh, Kamal, Rawat, Priyanka, Marouani, Sami, Jeudy, Baptiste
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2509.20595
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908558031847424
author Singh, Kamal
Rawat, Priyanka
Marouani, Sami
Jeudy, Baptiste
author_facet Singh, Kamal
Rawat, Priyanka
Marouani, Sami
Jeudy, Baptiste
contents Quality of Experience (QoE) modeling is crucial for optimizing video streaming services to capture the complex relationships between different features and user experience. We propose a novel approach to QoE modeling in video streaming applications using interpretable Machine Learning (ML) techniques over raw time series data. Unlike traditional black-box approaches, our method combines Kolmogorov-Arnold Networks (KANs) as an interpretable readout on top of compact frequency-domain features, allowing us to capture temporal information while retaining a transparent and explainable model. We evaluate our method on popular datasets and demonstrate its enhanced accuracy in QoE prediction, while offering transparency and interpretability.
format Preprint
id arxiv_https___arxiv_org_abs_2509_20595
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle TSKAN: Interpretable Machine Learning for QoE modeling over Time Series Data
Singh, Kamal
Rawat, Priyanka
Marouani, Sami
Jeudy, Baptiste
Machine Learning
Networking and Internet Architecture
Quality of Experience (QoE) modeling is crucial for optimizing video streaming services to capture the complex relationships between different features and user experience. We propose a novel approach to QoE modeling in video streaming applications using interpretable Machine Learning (ML) techniques over raw time series data. Unlike traditional black-box approaches, our method combines Kolmogorov-Arnold Networks (KANs) as an interpretable readout on top of compact frequency-domain features, allowing us to capture temporal information while retaining a transparent and explainable model. We evaluate our method on popular datasets and demonstrate its enhanced accuracy in QoE prediction, while offering transparency and interpretability.
title TSKAN: Interpretable Machine Learning for QoE modeling over Time Series Data
topic Machine Learning
Networking and Internet Architecture
url https://arxiv.org/abs/2509.20595