Insights
Published:
November 5, 2024
Author:
This is some text inside of a div block.

Case Study: Developing an AI Tool to Generate Match Reports

Share:
Lorem ipsum dolor sit amet, consectetur adipiscing elit. Suspendisse varius enim in eros elementum tristique. Duis cursus, mi quis viverra ornare, eros dolor interdum nulla, ut commodo diam libero vitae erat. Aenean faucibus nibh et justo cursus id rutrum lorem imperdiet. Nunc ut sem vitae risus tristique posuere.This is some text inside of a div block.

Providing Football Managers with an AI tool to create match reports.

The team at the Hartree Centre North East Hub worked with Sentr to develop an artificial intelligence tool to help Football Managers to create match reports, save time and boost engagement.

Challenge

Sentr is a new startup that has created a player engagement tool for amateur team sport managers. Sentr collects raw data from the team sport matches to populate a database and proceeds to turn that data into engaging, sharable content, such as graphics, and individual stats for each player. The challenge brought to the Hartree Centre North East Hub and the goal for this project was to increase user engagement by the team, within the app, through the creation of AI-generated match reports.

Approach

Data Scientists from the Hartree Centre NorthEast Hub worked with Sentr to explore the production of a proof-of-concept football match report generation tool, using their data for context. The initial stages involved understanding and exploring the domain, such as the required structure of match reports, to learn more about how to create a report that was well-structured and engaging for the players. The Hartree Data Scientists undertook experiments generating each section of the report separately, with code built to trial different Large Language Models (LLMs), parameters and prompts. The Data Scientists then worked with Sentr through an iterative process to improve the prompts used to create the reports, so that the code worked with fewer tokens and was simpler and more robust where necessary.

Benefits

The code and report produced by the Data Scientists at the Hartree Centre North East Hub will enable Sentr to demonstrate the ability to generate engaging match content using end-user (manager) data inputs. They have also received a framework to experiment with tuning the models and prompts to generate content, with models to be hosted on-premises or on Microsoft Azure cloud platform. As a result of the project, Sentr are looking towards integrating the proof-ofconcept match report generation into their platform, ready for use by end-users to increase engagement of players and users.

"Hartree Centre North East Hub has provided us with a viable means to generate templates for managers to entertain the players on their teams and increase user engagement on our app. Through the sessions we have been able to iterate and scope a robust large language model solution to generate content for the users of our app. This will allow us to release a key feature on our platform."
"Working alongside the Data Scientists from the Hartree Centre North East Hub was great. It has allowed us to explore artificial intelligence in a way that we haven’t before and it really felt like they were part of the team for twelve weeks."

- Andrew Charlton, Sentr

Further Information

This work was completed as part of one of our collaborative data projects. The projects are up to 12 weeks in duration and give you access to a wide range of expertise across our team of data scientists and data engineers. We will work alongside your team to scope your data science or engineering project, build a prototype solution, and explore options to deploy it within your organisation. You can learn more about them on our webpage here.

If you would like to learn more about the Hartree Centre North East Hub or our collaborative data projects, please get in touch with us at: hello@hartreenortheast.uk