Salary: Grade 7 (£37,099 – £44,263 p.a. depending on experience) 

This role will be based on the university campus, with scope for it to be undertaken in a hybrid manner. We are also open to discussing flexible working arrangements.

Do you have research expertise in Machine Learning with a specific focus on analysing human decisions and behaviour? Are you interested in conducting methodological research to develop new approaches? Would you like to implement novel methodologies to advance the state-of-the-art in behavioural modelling and make a real-world impact?

Understanding the mechanisms and the drivers behind people’s choices has been the focal point of a range of academic disciplines and a key component in policy making, for example aiming to shift behaviours for a more sustainable future. 

While models grounded in economic science and psychology are key tools in this area, competing approaches are emerging in the field of machine learning. While these methods offer potentially very good prediction performance, there are concerns about behavioural realism, and only limited knowledge spillovers into choice modelling and mathematical psychology, despite the shared core goal of understanding individual decision making. 

The synergy of distinct disciplines that all focus on behavioural models and the development of new state-of-the-art modelling frameworks holds the promise of providing new Data-Driven Behavioural Models (DDBMs) combining the strengths and addressing the distinct limitations of each area. The development of DDBMs will come at a time when big data sources constantly challenge traditional modelling approaches. Additionally, the growth in human-machine interactions, such as with the advent of autonomous vehicles, will require the development of AI consistent with human behaviour to guarantee public safety and wider adoption in the market. 

The Choice Modelling Centre at the Institute for Transport Studies seeks to hire an early career researcher to take part in the ERC-funded project “SYNERGY”. The project’s aim is to combine key techniques from Machine Learning, Choice Modelling and Mathematical Psychology, and help to develop new approaches. 

The role will involve working at the cutting edge of Machine Learning for analysing human decisions/behaviour, but with a keen focus on helping to build bridges across areas, helping to develop modelling frameworks that will actively shape future policy making. The successful candidate will need to demonstrate sufficient theoretical and technical knowledge in machine learning, and possess an open mind to new ideas and approaches. Knowledge of a programming language, with an emphasis on R and/or Python, is also strongly advised. 

As a member of the team, you will be based at the Institute for Transport Studies (ITS) where you will work with Professor Stephane Hess and other researchers in the Choice Modelling Centre (CMC), drawing also on expertise in its global network. You will become part of a highly productive team, have the opportunity to work with other groups in the University of Leeds and take part in international conferences for the purpose of disseminating the findings of the research. You are expected to contribute to methodological research on bridging choice modelling, mathematical psychology and machine learning in the context of transport, health and environment. As this is a multi-faceted research project, you will be able to contribute to individual components of the work as well as helping to shape the direction of the research according to your own interests and background. You will be expected to take academic ownership of large parts of the programme and make a lasting contribution to the field. 

What we offer in return

And much more!  

If you are looking for a role that will contribute to bridging the gap between machine learning and behavioural science, apply today.

To explore the post further or for any queries you may have, please contact: 

Stephane Hess, Professor of Choice Modelling, Director of the Choice Modelling Centre

Tel: +44 (0)113 343 6611

Email: [email protected]