• AI Guy
  • Posts
  • Using AI to build the perfect sports team

Using AI to build the perfect sports team

Moneyball part two?

By AI Guy ⏳ 4 min read

Howdy. This is AI Guy. The daily newsletter that sends you 1-2 interesting stories about AI straight to your inbox.

In Today’s edition:

🇬🇧 AI diagnoses cancer in the UK

⚽️ Using AI to build the perfect team

🔧 An incredible AI tool

🐤 Tweet of the day

AI tool diagnoses cancer in the UK 🇬🇧 🔎

Hospitals across the UK are rolling out an AI tool for doctors that quickly diagnoses early signs of cancer. Within seconds, the AI tool analyzes X-rays and catches early signs of illness that are overlooked by the human eye.

The British government has committed to rolling out a similar AI tool for stroke diagnosis which will be available by the end of 2023.

The use of AI in the British healthcare system has already had a positive impact on outcomes for patients. In some cases, AI is able to halve the time it takes to diagnose victims, saving critical time in the treatment process. Halving the time to diagnose a stroke has been shown to triple the probability that a victim is able to live independently after a stroke.

In the US, X-rays are the most common tool used to diagnose lung cancer – which is the third leading cause of cancer death in the nation. The deployment of diagnostic AI tools to more clinicians will greatly improve patient outcomes.

AI tools are already making a significant impact across the NHS in diagnosing conditions earlier

Steve Barclay – UK Health and Social Care Secretary

Using AI to build the perfect team ⚽️

Liverpool F.C. leads the way in soccer AI

Soccer came late to the sports analytics party.

Since its dawn in the 19th century, soccer has required decision-making based on the personal experience of individuals or a team.

While statistical analysis has, of course, become a key part of the modern game of football, baseball, and basketball, the game of soccer has lagged behind due to the endless variables and ever-changing nature of the game.

Baseball and Basketball lend themselves far more easily to data-based analysis because games are more regular. A baseball team plays 162 regular season games in a year, compared to just 38 games in the English Premier League.

With the help of AI, things are changing. The AI company DeepMind, which is owned by Google, has developed a model to make decisions for soccer coaches about scouting and positional tactics.

The tool is able to predict what individual players may do in unique situations given their historical play patterns.

The future of scouting.

To develop the model, Liverpool provided DeepMind with data on every Premier League game played between 2017 and 2019.

The DeepMind model uses ‘ghosting’ to speculate the likelihood of a certain outcome in a soccer situation. This is particularly useful when trying to scout players who would deal with specific types of match situations better than others.

In sporting terms, the ‘Moneyball’ technique, made famous by the Oakland A’s baseball team, involves a comprehensive statistical analysis in order to find players that exhibit underappreciated potential in their sport.

The use of AI would make the Moneyball technique even more efficient by understanding the playing technique of a club’s roster.

“Machine learning will be […] based on the players continuing their trajectories over the following decade”

Jason Stockwood, Chair of Grimsby Town F.C.

An incredible AI tool 👨‍💻

Ever feel like you have too many things to do, but not enough time to do them?

Ever wish u could have a little helper who could clear the small tasks off of your plate so you can focus on what you’re best at?

Introducing SuperCoder – An AI developer tool that acts as your personal intern, research assistant, and secretary that you can set up and let run in the background. 🏃‍♂️

How to use SuperCoder:

Step 1:

Create an account at https://superagi.com/ 

(we promise we’re not getting paid for this, we just think this product is incredible)

Step 2:

Use the open-source framework to build your autonomous agents quickly & reliably. You can ask the framework to perform tasks such as:

• Research a topic

• Reading & writing

• Web-scraping

• Data Analysis etc.

 

You could ask it more complicated prompts such as: “Research the effect of rising interest rates on the US housing market and write a one-page summary of what you’ve read. Then send the summary to our research channel on Slack”

Step 3:

Login to your AI agent into the necessary accounts (so that it can run in the background).

You can connect a long list of apps such as:

• Slack

• GitHub

• Image generation (DALL-E and Stable Diffusion)

• Coding tools

• Email

The possibilities are practically endless!

Tweet of the day 🐥

Thanks for reading! Stay AI-some!

You’re nerdy cousin,

AI Guy

Spread the word

Get your friends to join our base of subscribers and we’ll send you some Free AI Guy merch!

Reply

or to participate.