DIGITWISE: Digital Twin-based Modeling of Adaptive Video Streaming Engagement

2025-10-15

AI Summary

Traditional adaptive bitrate (ABR) algorithms overlook individual variations in user sensitivity to video artifacts and network fluctuations, leading to inaccurate engagement prediction—measured as the percentage of video watched before abandonment. This paper introduces the first digital twin–based framework for personalized engagement modeling, explicitly incorporating user-specific sensitivity into prediction. We construct user-level digital twins using XGBoost, trained on streaming event histories and supervised learning labels, enabling fine-grained behavioral modeling. The framework supports personalized content optimization and controlled A/B testing. Experiments demonstrate a 5.8% reduction in engagement prediction error compared to non-personalized baselines; after feature optimization, average engagement improves by up to 8.6%. Our core contribution is the first integration of individual sensitivity modeling into video streaming engagement prediction—advancing ABR design toward user-centric adaptation.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Computer Vision: Video Understanding & Activity Analysis
• Machine Learning: Online Learning & Bandits

Application Category

• User Modeling, Personalization and Recommendation: Metrics for user behavior and evaluating success
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

As the popularity of video streaming entertainment continues to grow, understanding how users engage with the content and react to its changes becomes a critical success factor for every stakeholder. User engagement, i.e., the percentage of video the user watches before quitting, is central to customer loyalty, content personalization, ad relevance, and A/B testing. This paper presents DIGITWISE, a digital twin-based approach for modeling adaptive video streaming engagement. Traditional adaptive bitrate (ABR) algorithms assume that all users react similarly to video streaming artifacts and network issues, neglecting individual user sensitivities. DIGITWISE leverages the concept of a digital twin, a digital replica of a physical entity, to model user engagement based on past viewing sessions. The digital twin receives input about streaming events and utilizes supervised machine learning to predict user engagement for a given session. The system model consists of a data processing pipeline, machine learning models acting as digital twins, and a unified model to predict engagement. DIGITWISE employs the XGBoost model in both digital twins and unified models. The proposed architecture demonstrates the importance of personal user sensitivities, reducing user engagement prediction error by up to 5.8% compared to non-user-aware models. Furthermore, DIGITWISE can optimize content provisioning and delivery by identifying the features that maximize engagement, providing an average engagement increase of up to 8.6%.

Problem

• Modeling individual user engagement in adaptive video streaming
• Addressing limitations of traditional ABR algorithms ignoring user sensitivities
• Predicting engagement using digital twins and machine learning

Innovation

• Digital twin-based modeling for user engagement prediction
• XGBoost machine learning models in digital twin architecture
• Personalized sensitivity-aware adaptive streaming error reduction