Training Machine Learning Models on Human Spatio-temporal Mobility Data: An Experimental Study [Experiment Paper]

2025-08-18

AI Summary

This work addresses the underexplored problem of long-term (multi-day to multi-week) full-trajectory prediction in human mobility modeling. Methodologically, we propose a macro-level lifestyle-pattern-aware trajectory forecasting framework that integrates weekday semantic encoding with user semantic clustering and hierarchical sampling to mitigate data skewness; employs a hybrid LSTM-Transformer architecture to jointly model user-specific historical behavior; and adopts mini-batch stochastic gradient optimization for robust training. Experimental results demonstrate that incorporating lifestyle-pattern semantics significantly improves prediction accuracy; semantic clustering and hierarchical sampling enhance model generalization; and mini-batch optimization exhibits superior robustness under data-scarce conditions. Our approach establishes a novel, interpretable, and scalable paradigm for long-horizon individual trajectory forecasting.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems

Application Category

• User Modeling, Personalization and Recommendation: Studies of user behavior, including longitudinal effects of personalized systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Web Mining and Content Analysis: Large pretrained models with web data

Abstract

Individual-level human mobility prediction has emerged as a significant topic of research with applications in infectious disease monitoring, child, and elderly care. Existing studies predominantly focus on the microscopic aspects of human trajectories: such as predicting short-term trajectories or the next location visited, while offering limited attention to macro-level mobility patterns and the corresponding life routines. In this paper, we focus on an underexplored problem in human mobility prediction: determining the best practices to train a machine learning model using historical data to forecast an individuals complete trajectory over the next days and weeks. In this experiment paper, we undertake a comprehensive experimental analysis of diverse models, parameter configurations, and training strategies, accompanied by an in-depth examination of the statistical distribution inherent in human mobility patterns. Our empirical evaluations encompass both Long Short-Term Memory and Transformer-based architectures, and further investigate how incorporating individual life patterns can enhance the effectiveness of the prediction. We show that explicitly including semantic information such as day-of-the-week and user-specific historical information can help the model better understand individual patterns of life and improve predictions. Moreover, since the absence of explicit user information is often missing due to user privacy, we show that the sampling of users may exacerbate data skewness and result in a substantial loss in predictive accuracy. To mitigate data imbalance and preserve diversity, we apply user semantic clustering with stratified sampling to ensure that the sampled dataset remains representative. Our results further show that small-batch stochastic gradient optimization improves model performance, especially when human mobility training data is limited.

Problem

• Training ML models to predict complete individual mobility trajectories
• Exploring macro-level mobility patterns and life routines in predictions
• Addressing data skewness and privacy in mobility prediction models

Innovation

• LSTM and Transformer models for trajectory prediction
• User semantic clustering with stratified sampling
• Small-batch stochastic gradient optimization technique