AI forecast the Premier League champion, but was it just luck?

  • An AI called Kickoff.ai, accurately predicted Manchester City’s triumph in the 2023/24 Premier League season.
  • While the AI accurately predicted some of the match results, other results went against its prediction.
  • Predictions have become a major part of the football viewing experience through XG or expected goals, and AI has the potential to take XG predictions one step further.

OUR TAKE
While AI can predict some of the results of the Premier League, its predictions are not always accurate. Therefore, more factors need to be considered in predicting the results.
–Audrey Huang, BTW reporter


The English Premier League came to an end with Manchester City eventually named champions. Last August, AI forecasted the Sky Blues would win the 2023/24 Premier League season. So it was right, but was it more than just luck?

Kickoff.ai’s prediction of the Premier League    

AI’s predictions of the 2023/24 Premier League season were mostly right: Manchester City winning and three correct teams in the four. Nevertheless, the results look slightly different at the bottom. The AI model predicted Burnley would have a strong season. Yet, it ranked second from bottom.

Also read: Dell shares drop as heavy AI investments expected to dent margin

Also read: Trend micro unveils AI tools to safeguard data at Computex

How does it work?

Kickoff.ai created a statistical machine learning model using data from previous season performances. By modelling the match, the team identified the result of the match. It uses a method called “Kickscore”, a rough measure of a team’s performance over time. Kickscore encodes how a model “sees” a team based on the data it has. “As it is dynamic, it is possible to interpret how a team’s strength evolved over the past decades,” explained the website.

Future of AI predictions in football

Predictions have become a major part of the football viewing experience through XG, and AI has the potential to take XG predictions one step further. “XG takes away some of the randomness of predictions,” Kickoff.ai’s Lucas Maystre explained. Moreover, the Kickoff.ai team suggests generative AI could help compile previously overlooked data into their prediction models

Audrey-Huang

Audrey Huang

Audrey Huang is an intern news reporter at Blue Tech Wave. She is interested in AI and startup stories. Send tips to a.huang@btw.media.

Related Posts

Leave a Reply

Your email address will not be published. Required fields are marked *