paper
A Comparative Study of Deep Learning Architectures for Multi-Horizon Behavioural Forecasting for Mobile Health
paperactiveprovisional
a-comparative-study-of-deep-learning-architectures-for-multi-horizon-behavioural-forecasting-for-mobile-health-51fb9c16·1 events·first seen 2d agoAliases: A Comparative Study of Deep Learning Architectures for Multi-Horizon Behavioural Forecasting for Mobile Health
Co-occurring entities
More like this (12)
Last-Mile Forecasting FrameworkBehavioral Trajectory Tracking Frameworktime-series forecastingZero Touch Predictive Orchestration: Automating Time-Series Models for the Cloud-Edge ContinuumDeepLearning.AIHierarchical Advantage Weighting for Online RL Fine-Tuning of VLAs from Sparse Episode OutcomesProbabilistic Time Series ForecastingMulti-Task LearningMulti-Agent Reinforcement Learning from Delayed Marketplace Feedback for Objective-Weight Adaptation in Three-Sided DispatchA Systematic Approach for Selecting Trajectories for Data AugmentationPredicting Future Behaviors in Reasoning Models Enables Better SteeringTime Series Foundation Models
Recent events (1)
Benchmark of deep learning architectures for multi-horizon behavioural forecasting in mobile health
A new arXiv preprint benchmarks six deep learning architectures, two zero-shot foundation models, and statistical baselines on multi-horizon behavioural forecasting from wearable and smartphone data across 800+ participants. Key findings include: no single architecture dominates (PatchTST leads among trained models), TimesFM matches or exceeds trained models zero-shot especially in low-data regimes, and participant-level fine-tuning reduces per-feature RMSE by 16–60%. The study is the first to jointly evaluate modern deep learning, foundation models, and personalisation for this domain.