5 ways AI is changing baseball – and big data is on the way

The increase of artificial intelligence (AI) has impacted every industry, but data mining in Major League Baseball (MLB) is the definition of a game changer.

“New data sources are coming online all the time,” said Oliver Dykstra, data engineer for the MLB Texas Rangers team. He told ZDNET that his job is to turn the information the organization collects into action a competitive advantage.

Also: Your AI transformation depends on these 5 business tactics

Dykstra has been with the Rangers since October 2022 and was part of the behind-the-scenes team supporting the players during their 2023 World Series victory.

“It was a great team to work with,” he said. “It’s amazing to see the immediate impact in real-life situations. I’ve never had a job where you can celebrate your wins the same way you can on a sports team.”

Dykstra learned some important lessons during his two years with the Rangers. Here are five ways AI and data are helping change baseball.

1. Make better predictions

Dykstra said the key thing he learned from using AI was the importance of data-driven predictions.

“We can run those scenarios a lot faster and have a better understanding of what’s going on out there,” he said. “It’s about being able to play around with these matches and run simulations to see how the match might play out if we brought this guy or that guy in or did a particular pitch sequence.”

Dykstra said his department has hundreds of models covering areas that continually release new information.

“From the top level, we make predictions for the whole season – how many wins we think we’ll get and the other teams in our division. We’ve been very accurate in 2023.”

Batting trends are another important area for prediction.

“In creating that play, you can get a pretty clear picture of where the batter is more likely to swing and miss,” he said.

Those insights could be crucial for pitchers. However, as with insight from any AI-powered project, the cultural impact of data use must be considered.

Also: 4 ways to turn innovative AI experiments into real business value

“You don’t become a pitcher by doing whatever someone tells you,” he said. “They’re very aware of where they are. So our job is to empower them as much as possible.”

2. Create new partnerships

Internal data talent is not the only important resource. The working relationships of successful MLB teams extend beyond the corporate sphere.

Dykstra said the Rangers collect data from a variety of sources and use it in combination Apache Airflow And Astronomer coordination and observation platform to ensure staff and players receive timely details.

“We wanted something that would be more dynamic and manageable, and give us a lot of insight,” he said.

Also: AI integration starts with a strong data foundation. Here are three strategies that executives use

Dykstra’s division works with Astronomer to help manage the Airflow deployment and the massive amount of data being processed.

“We’re working on more than just the professional level. Think about the dynamic nature of the game. At any given time, you could have one game going on in one day or 1,000 games across country and the world,” he said.

“The data flow is inconsistent, and if information in one of those parts starts taking longer, it can bring down the entire chain. Managing the supporting infrastructure will require a lot of maintenance work.” persistence and means we cannot look to the future.” as much as we want.”

3. Eliminate manual tasks

Dykstra describes baseball as a text-heavy industry. Rangers rely on scouts across the globe. Turning their written reports into useful data can be a difficult task — and that’s when Innovative AI (Gen AI) can help.

“There are a lot of terms and secret codes that scouts use,” he said. For one person to read all that information is too much and sometimes very confusing.” “Extracting value can be difficult. But with LLM and general AI, we can sort these summaries, providing a great dictionary for translating key phrases and summaries.”

Dykstra said much of the team’s work on Gen AI is exploratory, including a project that helps turn reconnaissance information into actionable insights.

Also: How your business can best exploit AI: Tell your board these 4 things

He said the organization used it Llama LLM. The franchise’s other technology partners, including Databricks and Amazon, support the investigation of additional models.

Rangers are also exploring how they can be used generation of retrieval enhancement to absorb the baseball rulebook and provide useful information to staff and spectators.

“That information changes a lot,” he said. An example could be healthcare and providing a chat interface for our people to explore the rules.”

“There are also rules for people visiting the stadium. They have questions, like ‘Can I bring a water bottle? Do I need a clear backpack?'”

4. Monitor other factors

Player data is not the only potential source of competitive advantage. Dykstra said the team also feeds its models with outside information, including weather data.

“This is an exciting new source,” he said. Every five minutes, we receive data from all different sectors.” “The dynamics of the weather in a stadium are not quite what you think they are. You can’t lift your finger. It’s not something you can necessarily get intuitively.”

Also: How to advance your work in the emerging AI economy

The Rangers’ home stadium, Globe Life Field, has a retractable roof and conditions can vary significantly from open stadiums in other locations across the United States.

“It’s important to give feedback to the players and say, ‘It’s not right. At home, it’s going to be a home run, so keep doing what you’re doing. That’s great. .’ They want that feedback immediately – they want it right after the game,” he said.

“The next day, they want to wake up and focus on the next game. The astronomer’s ability to respond to those data windows and deliver insights to our people as quickly as possible maybe after the game that will help settle things.”

5. Build a new culture

Industry experts say organizations must democratize access to data to take full advantage of the insights generated by emerging technologies.

Dykstra said that is exactly what happened at Rangers, especially the manager’s willingness to seize data-driven opportunities.

“I’m extremely impressed Bruce Bochy. “He brought the two worlds together and used his hunch to challenge any assumptions we were making,” he said.

Also: The future of computing must be more sustainable, even as AI requires greater energy use

Dykstra explained how the Rangers have a data analyst embedded within the team to help ensure coaches and players get the most out of the data: “It’s always a conversation.”

Of course, the widespread use of data can bring risks. He said the Rangers must comply with MLB’s strict rules and regulations.

“MLB greatly limits the types of feedback we can provide to our players and coaches during the game,” he said.

“Success is understanding how your data is moving, where it’s coming from, where it’s going, and being able to communicate that journey effectively. It’s a clear path.”