Elite players’ psychological profiles revealed using AI by analysts in the soccer world

“This players didn’t show enough fights. “When you hear Pandit’s post-match reaction, you can hear a variation in the sound bite.

In an age where soccer is increasingly leaning towards data to demonstrate physical attributes, it is difficult to provide statistics that accurately show players’ psychological qualities, such as emotional control and leadership. However, Premier League clubs, including Brighton, use techniques aimed at helping them choose and recruit.

Thomas Tuchel made headlines by telling England players to communicate more after assessing their interactions in the Euro 2024 final, but counting the players and talking to each other on the pitch, showing that only a portion of the mental battles are featured.

Former Norway and Denmark top flight defender Yo Amankwa is at the heart of the push for a better psychological evaluation of players. “When you take your eyes off the ball, it’s a treasure trove of information,” says Amankwa, who also works as a critic. “You can’t just ignore the tactics and look at the psychological parts of the game and the player through this lens, and you can’t see it. It’s a subtle, nonverbal message to show whether the player is very confident, aggressive, or a bubble of his own.”




“It’s impossible to just ignore tactics and look at the psychological parts of the game,” says Yo Amanka. Photo: Shipa/Aramie

Amankwah uses the example of a player who blew a 20-yard shot into the stands, and after 45 seconds he receives a comforting putt behind him from his passing teammate. It’s a fleeting moment that may be overlooked or overlooked by fans, the media, and even the coaching team, but for a former expert, it shows a quiet sense of leadership. “I know the clues and small actions you need to learn to function effectively on the football pitch,” says Amankwa.

Over the past six years he has worked with psychology professor Geir Jordet to analyze thousands of hours of match footage from around the world, including videos of all players from the Premier League and Women’s Super League. As a result, we have a dataset containing over 100,000 unique observations. This allowed the duo to create proxy rankings for players across different types of behavior via Duo (Inside Out Analytics).

This information can show whether the defender’s emotional control is in the top 5% of the league compared to opponents and teammates in the same position. As Jordette puts it, “It’s a new world. This map gives clubs a benchmark. You can see certain behaviors and count the number of times that occur in certain situations, but most can blind you to what it means.

“It’s hard to understand the exact meaning of them, but we’re no longer blind because, for this type of behavior, in this situation, if you compare all the players of this player in this Premier League, this player is in the 90th or 10th percentile.”

Bayern Munich is one of several major clubs trying out the platform, adopting technology in his time as head coach of Julian Nagelsmann. “All departments [in a club] You put numbers on the table, but psychology isn’t,” says Max Perka, a former Bavarian psychologist. [what is happening] On the pitch. ”




Max Perka (left) and Julian Nagelsmann worked together at RB Leipzig before moving to Bayern Munich. Photo: DPA/Aramie

Following Nagelsmann from RB Leipzig to Bayern, Perka worked with Jordet and Amankwa to analyze roughly 25 Bayern games in the second half of the 2022-23 season.

After each match, Pelka blocks detailed observations of each player’s posture, head movements, and hand gestures, leaving some elements of the body language monitored by Amankwah’s analytics team to a one-page summary of the side’s psychological performance. The data was one of several information sets that Nagelsmann and his assistants should consider before choosing a side.

Skip past newsletter promotions

“It was another variable that added to my idea of ​​choice,” Pelka says. “They could think if they really wanted a leader on their back four or if they wanted something else. [personality] option. ”


Players can also access an analysis of what Yoldett calls “the character of the game.” Perca said: [to play]. It doesn’t happen overnight, but if you have a starting point on how things look on the pitch, it’s much easier to work on. ”

Perca uses some of the techniques he employed in Munich to analyze Brighton’s players’ on-field behavior. He does not frequently monitor Fabian Hürzeler’s team, but the key board of the process is the same, with Brighton’s head coach reviewing a summary of key psychological “actions” on his part.

Jordet and Amnankwah are increasingly using artificial intelligence over manual coding, which consumed most of the pair’s time. “Soon there’s little limit to the number of teams you can analyze at any time, and we’ll actually start notifying the club about new signings in the future. “Yes, this seems like a good signature” or: “From our perspective, given these metrics, there’s a big red flag here and that’s what you might want to see.”

Source: www.theguardian.com

OpenAI set to launch “Deep-Search” tool designed to cater to research analysts

Openai has advanced artificial intelligence development by introducing a new tool that claims to produce reports comparable to those of research analysts.

Developers of Chatgpt have dubbed the tool “Deep Research,” stating that it can accomplish tasks that would take humans hours in just 10 minutes.

This announcement comes shortly after a San Francisco-based company accelerated its product release in response to the progress made by Openai’s competitor, Deepseek.

“Deep Research” is an AI agent that allows users to delegate tasks and is powered by Openai’s latest cutting-edge model, O3 version.

Openai explained that deep research scours hundreds of online sources, analyzes, integrates, creates comprehensive reports, and sifts through massive amounts of text, images, and PDFs.

The company views tools like the Chatgpt button as essential steps towards achieving artificial general intelligence, a concept that aims to match or exceed human intelligence in various tasks.

Last month, Openai unveiled an AI agent named Operator, claiming it can manage an online store based on photos of shopping lists, albeit only in the US preview version.

In a demonstration video released on Sunday, Openai showcased Deep Research analyzing the translation app market, stating that each task takes 5-30 minutes to complete with proper sourcing.

Openai highlighted that deep research targets experts in fields like finance, science, and engineering but can also be utilized for car and furniture purchases.

Leveraging Openai’s latest “reasoning” model, O3, deep research processes queries slower than traditional models and has a partially disclosed entity named O3-mini, a slimmed-down version of O3.

The full capabilities of the O3 model were outlined in the recent international AI safety report, prompting concerns from experts like Yoshua Bengio about the potential risks posed by AI advancements.

Skip past newsletter promotions

Deep surveys are accessible to Openai’s protia users in the US for $200 (£162 per month), with a monthly limit on queries due to processing constraints. Not available in the UK and Europe.

Andrew Rogoyski, director of an AI Research Institute affiliated with Sally University, cautioned about the potential dangers of blindly relying on deep search tools without conducting thorough verifications of their outputs.

“Knowledge-intensive AI faces a fundamental challenge. Human validation and verification are crucial to ensure the accuracy of machine analysis,” said Rogoyski.

Source: www.theguardian.com