, ,
In Intelligenza Artificiale, Dati Multisorgente e Analisi Avanzate per Sistemi Socio-Economici e Ambientali, 2025.
Roma, luglio 2026
Introduction
This paper explores how passive mobility data, including Mobile Network Operator (MNO) data, GPS traces and Floating Car Data (FCD), can complement official statistics by providing more timely and granular insights into mobility and tourism dynamics.
Through real-world applications in tourism, civil aviation and transport planning, the authors present methodologies that integrate multiple data sources using data fusion and machine learning techniques to generate reliable indicators for public and private decision-making.
The paper also examines the role of Large Language Models (LLMs) as natural-language interfaces for mobility analytics, enabling non-technical users to interact with complex datasets while maintaining data quality, transparency and statistical robustness.
By combining advanced analytics, artificial intelligence and multi-source data integration, the research highlights new opportunities to support sustainable tourism, transport planning and infrastructure management.
This publication builds upon the research presented in Enhancing Mobility and Tourism through Data Analytics and Generative AI (ASA Rome Conference, 2024), available here, extending it with new methodologies, additional case studies, data fusion techniques and the evaluation of Large Language Models.