Foundation Models for Tactical Understanding in Football (FOUND-Football)

About the Project

Project Description

The increasing availability of high-resolution football tracking data has transformed performance analysis, yet most existing machine learning approaches remain task-specific, league-dependent, and poorly transferable. Metrics such as expected goals, pass value, or pressing intensity are typically learned in isolation, limiting their ability to capture the underlying tactical structure of football matches and to generalise across teams, competitions, and playing styles.

This PhD project aims to develop foundation models for football analytics, learning general-purpose, transferable representations of football tactics directly from tracking data. Inspired by recent advances in foundation models across vision and language, the project will position football matches as complex spatio-temporal systems whose tactical structure can be learned through large-scale self-supervised learning.

Aims and Methods

The primary aims of the project are to:

(1) learn general tactical representations of football matches from tracking data;

(2) ensure transferability across leagues, teams, and seasons; and

(3) support downstream tactical analysis tasks through fine-tuning and probing.

Methodologically, the project will focus on:

• Representing football matches using spatio-temporal and graph-based structures, capturing player interactions, team shape, and space control over time;
• Self-supervised learning objectives tailored to football dynamics, such as masked trajectory prediction, future team-shape forecasting, interaction reconstruction, and contrastive learning across phases of play;
• Modern deep learning architectures, including graph transformers, spatio-temporal transformers, and hybrid graph–geometry models, designed to scale to full-match tracking data;
• Evaluating learned representations through downstream tasks such as tactical similarity, line-breaking propensity, pressing behaviour, and team-style embedding, with an emphasis on cross-league and cross-season transfer.

The project will emphasise representation quality and interpretability, rather than optimising a single performance metric, aiming to uncover reusable tactical abstractions that underpin multiple analytical tasks.

Deliverables

• A foundation-style representation learning framework for football tracking data
• Benchmarks for evaluating transferability and tactical generalisation
• Open-source implementations and curated datasets for football ML research
• Peer-reviewed publications in machine learning, sports analytics, and data science venues

Keywords

Football analytics; foundation models; self-supervised learning; graph neural networks; spatio-temporal modelling; tactical analysis; tracking data; representation learning

Contact for information on the project:

Dr Oktay Karakuş – karakuso@cardiff.ac.uk

How to Apply

This project is accepting applications all year round, for self-funded candidates.

Mode of Study: Full-time or part-time

Please submit your application viaComputer Science and Informatics - Study - Cardiff University

In the funding field of your application, indicate “I am applying for a self-funded PhD in Computer Science and Informatics”, and specify the project title and supervisors of this project in the text box provided.

Academic criteria: A 2:1 Honours undergraduate degree or a master's degree, in computing or a related subject. Applicants with appropriate professional experience are also considered. Degree-level mathematics (or equivalent) is required for research in some project areas.

Applicants must demonstrate English language proficiency. Students who do not have English as a first language must prove this by obtaining an IELTS score of at least 6.5 overall, with a minimum of 6.0 in each skills component. A full list of accepted qualifications is available here: https://www.cardiff.ac.uk/study/international/english-language-requirements/postgraduate

If you are interested, please contact Dr Oktay Karakus (karakuso@cardiff.ac.uk) sending your CV in the first instance. The application process requires you to develop an individual research proposal jointly with the supervision team, which builds on the information provided in this advert.

Once you have developed the proposal with support from the supervisors, please submit your application following the instructions provided below.

Please submit your application viaComputer Science and Informatics - Study - Cardiff University

In order to be considered candidates must submit the following information:

• In the ‘Research Proposal’ section of the application enter the name of the project you are applying to and upload your Individual research proposal. Your research proposal should not exceed 2000 words, including references and bibliography.
• A personal statement (as part of the university application form, or as a separate attachment, if you prefer).
• A CV. Guidance on CVs for a PhD position can be found on the FindAPhD website.
• Qualification certificates and Transcripts - original and English translation, if applicable.
• References x 2 which should be academic references. Please note you need to provide the reference documents as part of your application.
• Proof of English language (if applicable).

Interview– If the application meets all ofthe entrance requirements listed above, you will be invited to an interview.

Funding Notes

This project is offered for self-funded students only, or those with their own sponsorship or scholarship award. Where applicable, candidates will be required to cover the cost of a student visa, the healthcare surcharge, and any other costs of moving to the UK to study. These costs will not be covered by the School of Computer Science and Informatics.