TacticAI: New Model From Google DeepMind Brings AI To Football

Mar 20, 2024 | 0 comments

Image Credits: Google DeepMind

Google DeepMind, in collaboration with Liverpool F.C., developed an AI model known as TacticAI, which helps to assist and guide coaches for corner tactics in the game of football. 

A corner is given to a team when a football passes over the goal line after touching any player of the opposite team. A corner is a crucial part of the game, as it can result in a goal and change the whole game. 

How TacticAI Helps

TacticAI was trained on a dataset of more than 7,000 corner kicks from the 2020–21 Premier League season. The model leverages a combination of predictive and generative AI models. These capabilities help to predict which player will receive the ball while taking a corner kick, the result of a corner kick, and help to adjust player setup. It gives advice on both defending and attacking corners in the game. 

It helps coaches analyze and enhance the corner kick strategies by advising about position changes of the players that can result in a better output.

Previously, analysts needed to watch many videos from previous games to study rival teams and look for similar examples in a game. TacticAI automatically computes the numerical representations of players, thereby helping analysts by allowing them to view relevant past routines without needing to watch previous games.

Liverpool’s experts were shown various corner setups, some of which were TacticAI suggestions and some that were previously used. The experts were asked to choose between the two, and they preferred TacticAI-suggested tactics 90% of the time.

You can read TacticAI’s paper from Google DeepMind to know more about the model.


With increasing competitiveness in sports, every team wants to be the best. So technology is always helpful in advising what should be done. Many sports teams are currently using previous game data to make decisions, and it sometimes works for them.

Sports games like football are very random, which makes it difficult to get a good dataset for AI models to work on, but TacticAI was able to give great tactical insights that are practical on the field. This shows that sports can be another area where we might see AI being largely used.

Read More

DeepMind’s Cofounder Mustafa Suleyman Joins as CEO of Microsoft AI

Stable Video 3D Unveiled by Stability AI: Now Generate 3D Orbital Videos from Simple Images


Elon Musk’s xAI Announces Grok 1.5 with Great Capabilities

Elon Musk’s xAI Announces Grok 1.5 with Great Capabilities

Image Credits: xAI Elon Musk's xAI launched Grok last year in November to compete with chatbots from big tech giants like Google, Microsoft, and OpenAI. Elon Musk's xAI is soon launching the next version of their chatbot, Grok 1.5, which performs really well as...

Meta’s Ray-Ban Smart Glasses Are Getting New AI Features

Meta’s Ray-Ban Smart Glasses Are Getting New AI Features

Image Credits: Meta Meta’s $300 smart glasses, made in collaboration with Ray-Ban, allow users to take pictures, record videos, make calls, hear music, and do much more. Now, new AI features are being added to Meta's Ray-Ban smart glasses.  New AI Features in Meta’s...

Claude 3 beats GPT-4 for the First Time on LMSYS Leaderboard

Claude 3 beats GPT-4 for the First Time on LMSYS Leaderboard

Anthropic released the Claude 3 model family earlier this month, and they have become highly popular since their release. Now Anthropic's Claude 3 Opus Model beats OpenAI's GPT-4 model for the first time on the LMSYS Chatbot Arena Leaderboard. LMSYS Chatbot Arena is a...


Submit a Comment

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