Following the deadline for submissions, the Pro Forum judges spent November and December reviewing dozens of presentation proposals for the 2021 event, which will be taking place online on Wednesday 24th March.
The judges scored each proposal, which were anonymised, based on three key criteria: innovation, relevance and application. By the end of the process, five projects had been chosen for presentation, with a further submitter getting the opportunity to exhibit their proposal on a digital poster after being named as the inaugural winner of the Dr. Garry Gelade award.
Now entering its eighth year, the Forum remains a key date in the football analytics calendar, showcasing innovative approaches to key questions relating to performance analysis and recruitment to industry professionals working at over 80 clubs and federations worldwide. For 2021 the event has partnered with the French Football League (LFP), who will be making historical Ligue 1 Uber Eats tracking data available to help presenters attain deeper insights into performance.
The full line-up for the 2021 Forum, listed in no specific order, is as follows:
Debangan Dey, Rahul Ghosal and Atanu Mitra – Enriching event data: A semi-supervised augmentation approach using location information
This presentation introduces a method for utilising tracking data to extract more information from an event-only match dataset. Using a merged dataset where both tracking and event data is available, this project will take a semi-supervised approach to creating predictive models that capture hidden patterns from within this dataset with the objective of drawing inferences for tracking data in an event-only dataset.
Based in the United States, Debangan is currently completing a PhD in Biostatistics at the John Hopkins Bloomberg School of Public Health in Baltimore, where Rahul is also a Postdoctoral Fellow. Atanu is a Data Scientist at Transunion based out of Mumbai, India.
Caterina De Bacco – Identifying and evaluating the efficiency of each player during the pressing phase against an opponent’s controlled build-up play
This project was chosen in the first of the Forum’s two club-led submission categories, set by Alexander Schmalhofer of Red Bull Soccer International, which proposes the creation of three measurable KPIs for scoring individual defensive players during a team’s press.
Taking into account that pressing is not limited to turning over the ball, but is also connected to stopping events from happening, such as a pass being attempted through intelligent positioning, the three KPIs include a ball recovery score, an interception opportunity score and a surface covering score, with scores for all three metrics being calculated at each stage of an opposition’s build-up play. These outputs can help a team objectively evaluate the effectiveness of each player during their coordinated pressing actions, informing development and refining future pressing execution.
Caterina holds a PhD in Statistical Physics and is currently an Independent Research Group Leader at Cyber Valley, Max Planck Institute for Intelligent Systems in Tübingen, Germany.
Aditya Kothari – A physics based measurement of defensive contributions
Aditya’s presentation introduces a model for applying tracking data to quantify the performance of a player’s defensive contributions on the pitch. Focusing on pass and carry prevention and shot prevention, Aditya will build on existing pitch control modelling work with the aim of identifying how well defending teams and individual defenders perform in particular situations during a game, identifying weaknesses and lapses in the defensive system and picking up on other unusual occurrences.
Aditya leads the data science team at Ather Energy, based out of Bengaluru, India. He also tweets football data science related content from @thecomeonman.
Ola Lidmark Eriksson – Volatility and calculation of risk-adjusted return in football scouting
Within the financial sector, the Sharpe ratio model has been used by analysts for decades to measure the performance of stocks and how they fluctuate over time. In professional football, having a good understanding of volatility in a player’s performances over time would be of considerable value to a recruitment department when assessing players, particularly in relation to player age.
In this project, Ola will be applying Opta data to generate player KPIs from key metrics and will then use the Sharpe ratio to calculate the volatility of each player’s performance over time, to identify players who display greater consistency and those whose performance changes from game-to-game.
Based in Sweden, Ola is a data scientist who provides consultancy services to a number of clubs and media outlets in his homeland. He also appears as an analyst on Fotbollslabbet, a football analytics show broadcast on the Swedish channel TV4.
Vignesh Jayanth – Identifying and evaluating strategies for successfully penetrating a high opposition press from short goal kicks, played inside the box, to move the ball into the opposition half
In the second of the Forum’s club-led submission categories, set by Lucy Rushton, Vignesh’s presentation focuses on an approach to identify and evaluate the best-attacking strategies to penetrate a high opposition press from short goal kicks.
Through applying tracking and event data, Vignesh’s project will look to define a high opposition press by measuring the density of players at a given distance from the goal line, by breaking the pitch down into nine zones. A hybrid recommender system will then combine zone interactions and player positions to make recommendations on team’s who share a similar approach and finally, he will look to identify attacking strategies by understanding underloaded and overloaded zones in this phase.
This is the second successive year that Vignesh has been chosen to present at the Forum, having delivered a presentation in 2020 on strategies for breaking down a low block defence. Since last year’s Forum, he has undertaken consultancy work on behalf of clubs based in England and Denmark, alongside his full-time work as a data scientist.
Dr. Garry Gelade Award Winner
In tribute to one of the football industry’s leading analytics pioneers, Dr. Garry Gelade, who sadly passed away last year, a new award has been set-up in his memory to recognise the outstanding submission from an undergraduate.
We are pleased to announce that the inaugural winner of the Dr. Garry Gelade award is Laurynas Raudonius, who is studying Computer Science at The University of Manchester.
Laurynas’ project, titled Recognizing and evaluating opportunities in counterattacks using tracking data, proposes the application of spatio-temporal data to recognize a team’s offensive opportunities after winning the ball and will use Voronoi cells to assess what actions lead to a successful counter attack.
As part of his award, Laurynas will receive mentoring from Stats Perform’s AI Insights team to help complete his project. His findings will be displayed on a digital poster presentation at the Forum.
Stats Perform would like to thank everyone who submitted a proposal as well as the panel of judges, and congratulate the six people who will be presenting or showcasing a poster at the 2021 Pro Forum.