Skip to main content

Developing new behavioural models at the intersection of econometrics and machine learning


Key facts

Type of research degree
Application deadline
Ongoing deadline
Project start date
Tuesday 1 October 2024
Country eligibility
International (open to all nationalities, including the UK)
Source of funding
Research council
Professor Stephane Hess
Additional supervisors
Dr Panos Tsoleridis
Institute for Transport Studies
<h2 class="heading hide-accessible">Summary</h2>

We are looking for a highly motivated student to conduct PhD research in the field of choice modelling. Choice modelling is a key analytical tool used to understand consumer decisions and valuations and forecast choices across a range of topic areas, including transport, environmental and health economics, and regional science. Their outputs form a key component in guidance underpinning government and industry decisions on changes to policy, infrastructure developments or the introduction of new services or products. This role provides an exciting opportunity to contribute to a major cross-disciplinary research programme at the heart of the Choice Modelling Centre ( set up within the University of Leeds. The five year SYNERGY project, funded by the European Research Council (ERC) seeks to unify three key paradigms for the mathematical modelling of human behaviour, namely: i) process models in psychology and cognate disciplines that seek to explain how decisions are made; ii) econometric and behavioural models that explain which factors influence the decision process and to what extent; and iii) data-driven (machine learning) methods that focus on the outcome of the decision process. The different aims and assumptions of these paradigms have resulted in very distinct strengths and weaknesses for each discipline. Only the synergy of the three will fulfil the promise of producing models that are behaviourally consistent, applicable to real-world problems, computationally tractable, and balance a priori assumptions with data-driven insights.

<h2 class="heading hide-accessible">Full description</h2>

<p style="margin-bottom:11px">The aim of this PhD project is to specifically create more links between two out of the three paradigms: econometric/behavioural models and machine learning algorithms. In recent years, machine learning algorithms have steadily gained attention in the context of modelling individual decision making processes and are challenging traditional econometric approaches with their increased prediction performances and their ability to handle complex datasets. Both approaches seek to understand individual choice behaviour, but from a different perspective putting attention on different aspects: econometric approaches seek to understand the parameters influencing observed behaviour and their impact on the choice itself; machine learning algorithms seek to predict the outcome of the choice by taking a data-driven approach and finding complex associations within the data. While attention so far has primarily been on comparing and contrasting those two methods, there are potential benefits to be gained by combining them. In particular, the research could establish best practices for comparing/combining the approaches, and develop new methods for integrating machine learning components with econometric specifications.</p> <p><strong>Tentative research questions:</strong></p> <p>The research is likely to evolve over the course of the PhD, but will for example seek to address the following questions:</p> <ul> <li>What is the point of departure of machine learning algorithms from the traditional econometric approaches?</li> <li>What elements of machine learning algorithms can be used as part of econometric models to increase prediction performance while still having interpretable parameters?</li> <li>Are specific types of datasets or research questions better suited to one method over the other?</li> <li>What is the level of abstraction required to achieve good prediction performance on hold-out samples?</li> </ul> <p><strong>Funding start date is flexible but must be taken up by 1<sup>st</sup>&nbsp;October 2024.</strong></p>

<h2 class="heading">How to apply</h2>

<p>Formal applications for research degree study should be made online through the&nbsp;<a href="">University&#39;s website</a>. Please state clearly in the research information section&nbsp;that the research degree you wish to be considered for is Developing new behavioural models at the intersection of econometrics and machine learning as well as <a href="">Professor Stephane Hess</a> as your proposed supervisor.</p> <p>If English is not your first language, you must provide evidence that you meet the University&#39;s minimum English language requirements (below).</p> <p><em>As an international research-intensive university, we welcome students from all walks of life and from across the world. We foster an inclusive environment where all can flourish and prosper, and we are proud of our strong commitment to student education. Across all Faculties we are dedicated to diversifying our community and we welcome the unique contributions that individuals can bring, and particularly encourage applications from, but not limited to Black, Asian, people who belong to a minority ethnic community, people who identify as LGBT+ and people with disabilities. Applicants will always be selected based on merit and ability.</em></p>

<h2 class="heading heading--sm">Entry requirements</h2>

A first class (or equivalent) postgraduate degree related to Computer Science, Mathematics or Statistics from a reputed university is desirable. Candidates with an upper second class (or equivalent) degree from excellent universities will also be considered, especially if the candidate has a Masters degree and/or practical experience in a highly relevant area. Experience of machine learning, statistical modelling and programming skills in R and/or Python is also desirable.

<h2 class="heading heading--sm">English language requirements</h2>

The minimum English language entry requirement for research postgraduate research study is an IELTS of 6.0 overall with at least 5.5 in each component (reading, writing, listening and speaking) or equivalent. The test must be dated within two years of the start date of the course in order to be valid. Some schools and faculties have a higher requirement.

<h2 class="heading">Funding on offer</h2>

<p style="margin-bottom:11px">An enhanced stipend of &pound;18,905 per year (figure for 2023/2024) is available for a duration of 3 years plus fees.</p>

<h2 class="heading">Contact details</h2>

<p>Enquiries, including on how to apply and funding details, may be made via telephone/email to <a href="">Professor Stephane Hess | Institute for Transport Studies | University of Leeds</a> and <a href="">Dr. Panos Tsoleridis | Institute for Transport Studies | University of Leeds</a></p>