School of Mathematics, Statistics & Actuarial Science

Events calendar

Oct 19
14:05 - 14:55
Statistics seminar: Mark Girolami, Imperial

Title: Stochastic Modelling of Urban Structure

Abstract: Urban systems are complex in nature and comprise of a large number of individuals that act according to utility, a measure of net benefit pertaining to preferences. The actions of individuals give rise to an emergent behaviour, creating the so-called urban structure that we observe. In this talk, I develop a stochastic model of urban structure to formally account for uncertainty arising from the complex behaviour. We further use this stochastic model to infer the components of a utility function from observed urban structure. This is a more powerful modelling framework in comparison to the ubiquitous discrete choice models that are of limited use for complex systems, in which the overall preferences of individuals are difficult to ascertain. We model urban structure as a realization of a Boltzmann distribution that is the invariant distribution of a related stochastic differential equation (SDE) that describes the dynamics of the urban system. Our specification of Boltzmann distribution assigns higher probability to stable configurations, in the sense that consumer surplus (demand) is balanced with running costs (supply), as characterized by a potential function. We specify a Bayesian hierarchical model to infer the components of a utility function from observed structure. Our model is doubly-intractable and poses significant computational challenges that we overcome using recent advances in Markov chain Monte Carlo (MCMC) methods. We demonstrate our methodology with case studies on the London retail system and airports in England.


Cornwallis North West,
University of Kent,
United Kingdom


Contact: Silvia Montagna



School of Mathematics, Statistics and Actuarial Science (SMSAS), Sibson Building, Parkwood Road, Canterbury, CT2 7FS

Contact us

Last Updated: 27/04/2017