A data analytics approach to identifying doping risk indicators – development of a doping suspect prioritisation tool

Supervised by Professor Ian Boardley and Dr Rowland Seymour together with UK Anti-Doping

To apply for this project, please include ‘Boardley & UK Anti-Doping’ as the project descriptor in the subject heading of your email.

United Kingdom Anti-Doping (UKAD) is the UK’s National Anti-Doping Organisation responsible for protecting clean sport in the UK. It is accountable to the Department for Culture, Media and Sport and governed by a worldwide agreed set of rules, the World Anti-Doping Agency’s (WADA) Code. UKAD is responsible for testing and sanctioning athletes for use of prohibited substances and methods as well as associated violations of the Code and delivers a world-class anti-doping education programme to athletes and Athlete Support Personnel.

This collaborative doctoral studentship addresses a key organisational objective for anti-doping organisations such as UKAD, by seeking to develop methods to identify athletes most at risk of doping. As stipulated by the World Anti-Doping Code and the International Standard for Testing and Investigations, anti-doping organisations are required to undertake sports-based risk assessments to categorise levels of doping risk and to inform the development of an athlete testing programme. This risk assessment must include components such as the physiological requirements of the sport/discipline, which prohibited substances and/or prohibited methods would most likely enhance performance, the rewards and/or potential incentives for doping and the doping history in each sport. One of the aims of this project will be to help UKAD further develop their risk assessment model to identify individuals at highest risk for doping by taking a data analytics approach to identify doping behaviours and risk indicators, understand their effect on the level of doping risk, and examine the interplay between these factors. In addition, the project will investigate whether mathematical-modelling-based risk prediction methodologies can be used to predict doping behaviour. 

We are looking for an exceptionally talented and dedicated PhD student with a 1st class or 2:1 degree in the field of sport science, psychology, mathematics, computer science or a combination of these fields. Applicants without a background in mathematics or statistics would need to develop skills in these areas as part of their studies. An MSc degree in a relevant area is desirable though not necessary. Previous experience with elite sport, anti-doping education, anti-doping testing, data science, statistical modelling and/or an interest in pursuing a career relevant to clean sport are all desirable. 

Informal enquiries about the project prior to application can be directed to Professor Ian Boardley (I.d.boardley@bham.ac.uk) or Dr Rowland Seymour (R.G.Seymour@bham.ac.uk).