Machine Learning Models for YouTube QoE and User Engagement Prediction in Smartphones

Abstract : Measuring and monitoring YouTube Quality of Experience is a challenging task, especially when dealing with cellular networks and smartphone users. Using a large-scale database of crowdsourced YouTube-QoE measurements in smartphones, we conceive multiple machine-learning models to infer different YouTube-QoE-relevant metrics and user-behavior-related metrics from network-level measurements, without requiring root access to the smartphone, video-player embedding, or any other reverse-engineering-like approaches. The dataset includes measurements from more than 360 users worldwide, spanning over the last five years. Our preliminary results suggest that QoE-based monitoring of YouTube mobile can be realized through machine learning models with high accuracy, relying only on network-related features and without accessing any higher-layer metric to perform the estimations.
Liste complète des métadonnées

https://hal.inria.fr/hal-01898083
Contributor : Sarah Wassermann <>
Submitted on : Thursday, October 18, 2018 - 2:59:20 AM
Last modification on : Friday, October 19, 2018 - 1:13:10 AM
Document(s) archivé(s) le : Saturday, January 19, 2019 - 12:21:13 PM

File

WAIN_2018_camera_ready_paper_1...
Files produced by the author(s)

Identifiers

  • HAL Id : hal-01898083, version 1

Collections

Citation

Sarah Wassermann, Nikolas Wehner, Pedro Casas. Machine Learning Models for YouTube QoE and User Engagement Prediction in Smartphones. Workshop on AI in Networks (WAIN) 2018, Dec 2018, Toulouse, France. ⟨hal-01898083⟩

Share

Metrics

Record views

60

Files downloads

159