Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  Explaining and predicting travel behaviour using data collected by mobile phones

   School of Computing, Engineering & the Built Environment

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Dr A Fonzone, Dr G Fountas  No more applications being accepted  Self-Funded PhD Students Only

About the Project

The transport sector is undergoing fast and profound transformations that open stimulating research questions. Solving them means to improve a big part of the lives of millions of people:

Statistics from the Department for Transport show that on average each person spends 370 hours a year travelling. The limitations due to the COVID-19 outbreak have put in front of everyone’s eyes how crucial mobility is for the quality of life of people and a thriving society. Travelling within and between cities follows increasingly complicated patterns that rely on a plethora means of transport, ranging from more traditional means like private cars and conventional forms of mass transport to more innovative but already established services like ride-hailing (e.g. Uber) and shared vehicles (car clubs but also shared bikes), to the emerging micro-mobility systems (the e-scooters are currently under trial in the UK). The business model of transport provision is evolving towards Mobility as a Service, in which transport services of different kinds are integrated and offered through an intelligent platform in a user-centric system.

Planning, operating, and evaluating mobility systems in such a dynamic and multifaceted environment requires a clear understanding of travel behaviour. In the past, such an understanding had to rely on surveys of limited scope and granularity. The diffusion of mobile apps has made it possible to collect large and rich datasets passively, thus increasing the information available to researchers, practitioners, operators, and decision-makers.

We have access to one of such datasets, collected from the users of an open-source mobile app for multi-modal information, OneBusAway. For each trip made by the participants in the study, the dataset includes information on origin and destination, means of transport and duration of each leg of the trip, and the interactions with the app itself (a detailed description of characteristics of the app and of the data it can collect is available here.

The dataset offers a unique opportunity for exciting research on travel decision-making. In your PhD, you can use the data either to understand how people make their travel choices (the trip and personal characteristics affecting the choices and their importance, the temporal evolution of the decisions, and the impact of real-time information on the decision -making process) or to predict the choices from the historical behaviour. Depending on your interests and skills, you can approach the problem using discrete choice modelling or artificial intelligence techniques or a mix of the two. You will develop your project in collaboration with our partner universities in the US and Japan.

Academic qualifications

A first degree (at least a 2.1) ideally in statistics/econometrics/applied mathematics/data science/computer science/transportation with a good fundamental knowledge of transport planning and statistical and econometric techniques or artificial intelligence.

English language requirement

IELTS score must be at least 6.5 (with not less than 6.0 in each of the four components). Other, equivalent qualifications will be accepted. Full details of the University’s policy are available online.

Essential attributes:

· Experience of fundamental statistical or artificial intelligence methods for data analysis, processing large datasets

· Competent in transport analysis and planning, computer programming languages (e.g., Python, R) · Knowledge of data collection for transport planning · Good written and oral communication skills · Strong motivation, with evidence of independent research skills relevant to the project · Good time management Desirable attributes: Experience of academic writing

Engineering (12)


Chen, C., Ma, J., Susilo, Y., Liu, Y. and Wang, M., 2016. The promises of big data and small data for travel behavior (aka human mobility) analysis. Transportation research part C: emerging Kong, X., Li, M., Ma, K., Tian, K., Wang, M., Ning, Z. and Xia, F., 2018. Big trajectory data: A survey of applications and services. IEEE Access, 6, pp.58295-58306.technologies, 68, pp.285-299. Ma, X., Liu, C., Wen, H., Wang, Y. and Wu, Y.J., 2017. Understanding commuting patterns using transit smart card data. Journal of Transport Geography, 58, pp.135-145.

 About the Project