Next-Generation Travel Demand Modeling with a Generative Framework for Household Activity Coordination

2025-07-09

AI Summary

Traditional activity-based travel demand models (ABMs) rely on simplified behavioral heuristics, resulting in high development costs and poor transferability across regions. To address these limitations, this paper proposes a fully generative, data-driven modeling paradigm that integrates population synthesis, activity chain generation, location assignment, and large-scale microscopic traffic simulation in an end-to-end manner—eliminating hand-crafted behavioral assumptions and enabling lightweight, rapidly deployable models across diverse urban contexts. The approach synergistically combines deep generative models with statistical synthesis algorithms, scaling to metropolitan areas with populations exceeding ten million. Empirical evaluation in Los Angeles demonstrates high fidelity: OD matrix cosine similarity of 0.97; VMT Jensen–Shannon divergence (JSD) of 0.006 (MAPE = 9.8%); and corridor-level speed and flow JSD of 0.001 (MAPE = 6.11%). These results significantly outperform conventional ABMs, validating the framework’s accuracy, scalability, and generalizability.

Technology Category

• Search and Optimization: Sampling/Simulation-based Search
• Planning, Routing, and Scheduling: Model-Based Reasoning
• Natural Language Processing: Generation

Application Category

• Web Mining and Content Analysis: Web data generation and simulation
• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Social Networks and Social Media: Generative AI / large language models and their impact on social systems

Abstract

Travel demand models are critical tools for planning, policy, and mobility system design. Traditional activity-based models (ABMs), although grounded in behavioral theories, often rely on simplified rules and assumptions, and are costly to develop and difficult to adapt across different regions. This paper presents a learning-based travel demand modeling framework that synthesizes household-coordinated daily activity patterns based on a household's socio-demographic profiles. The whole framework integrates population synthesis, coordinated activity generation, location assignment, and large-scale microscopic traffic simulation into a unified system. It is fully generative, data-driven, scalable, and transferable to other regions. A full-pipeline implementation is conducted in Los Angeles with a 10 million population. Comprehensive validation shows that the model closely replicates real-world mobility patterns and matches the performance of legacy ABMs with significantly reduced modeling cost and greater scalability. With respect to the SCAG ABM benchmark, the origin-destination matrix achieves a cosine similarity of 0.97, and the daily vehicle miles traveled (VMT) in the network yields a 0.006 Jensen-Shannon Divergence (JSD) and a 9.8% mean absolute percentage error (MAPE). When compared to real-world observations from Caltrans PeMS, the evaluation on corridor-level traffic speed and volume reaches a 0.001 JSD and a 6.11% MAPE.

Problem

• Develops a generative framework for household activity coordination in travel demand modeling
• Addresses high cost and limited adaptability of traditional activity-based models
• Validates model accuracy and scalability using real-world mobility data

Innovation

• Generative framework for household activity coordination
• Data-driven and scalable travel demand modeling
• Integrated population synthesis and traffic simulation