Sep 6 – 10, 2026
Centro Didattico Morgagni
Europe/Rome timezone

Tourist Mobility: A Markov Chain Approach Using Origin--Destination Survey Data

Not scheduled
20m
Centro Didattico Morgagni

Centro Didattico Morgagni

Viale Morgagni 40, Firenze
Statistical / Stochastic Modelling and Statistical Computing

Speaker

Ms francesca atzori (university of Cagliari)

Description

This study develops a data-driven Markov chain framework to analyse tourist mobility patterns using empirical origin–destination data collected through surveys at a tourism information point. The dataset records both the municipality visited immediately prior to the survey and the subsequent intended destination, enabling the estimation of transition probability matrices that govern the stochastic evolution of tourist flows. To capture behavioural heterogeneity, separate transition matrices are constructed for two age groups (15–35 and 36–55), and Monte Carlo simulations are performed to examine long-run visitation distributions. The results reveal significant differences in destination preferences across age cohorts and show that the survey location primarily functions as a transit node rather than a final destination. From an economic perspective, the findings provide insights into the spatial allocation of tourism demand and the connectivity structure of local destinations. Identifying high-probability transitions and persistent visitation patterns can support more effective destination management, targeted marketing strategies, and improved allocation of local resources. More broadly, the study demonstrates how partial mobility data can be integrated into a stochastic modelling framework to extract statistically robust and economically meaningful information, offering a flexible tool for the analysis and planning of tourism systems.

Classification Both methodology and application
Keywords Tourist mobility, Markov chains, Tourism flows, Destination management

Primary author

Ms francesca atzori (university of Cagliari)

Presentation materials

There are no materials yet.