How Major League Baseball is using artificial intelligence and machine learning to change the national pastime.

Artificial intelligence (AI) is rapidly transforming the world of Major League Baseball (MLB). You may have heard of ChatGPT (which is a language model) from OpenAI mentioned in the news lately, but there is much more to modern AI. From player performance analysis to in-game decision-making, AI is revolutionizing the way coaches, managers, and scouts approach the game. With advancements in data driven technology and data analytics, AI is providing deeper insights into player performance, pitch tracking, and fan engagement. In this article, we’ll explore the ways AI is shaping the future of MLB teams and the impact it’s having on the sport. We’ll also examine the potential implications of AI on baseball and what the future may hold for this ever-evolving technology. Unlike other trends, you don’t need to be a big market team in New York or Los Angeles to take advantage of this technology to help you reach the World Series, in fact there are now many high schools leveraging it.

Player Performance Analysis

There are several ways that AI is being used to analyze player performance data, including:

1. Sensor data analysis: One way that AI is being used to analyze player performance is through the analysis of sensor data. Many baseball players now wear sensors on their bats, gloves, and bodies during games and practices, which can provide valuable data on things like swing speed, ball spin, and arm velocity in real-time. AI algorithms can be used to analyze this data and identify patterns in a player’s performance that may not be immediately obvious to coaches or scouts. The most common metrics that have caught on lately is launch angle and exit velocity of home runs.
2. Video analysis: Another way that AI is being used to analyze player performance is through the analysis of video data. Pitching coaches, hitting coaches, and scouts can use video footage of games and practices to identify areas where a player may need improvement, such as their swing or throwing motion. AI algorithms (computer vision) can be used to analyze this video data and provide insights into a player’s performance that may not be apparent to the naked eye.
3. Performance modeling: AI can also be used to create performance models of players based on their performance data. For example, an AI algorithm could use data on a player’s swing speed, contact rate, and other metrics to create a model of how that player is likely to perform in certain situations. This information can be used by player development coaches and scouts to make better decisions about player selection, training, and development.
4. Injury prevention: Finally, AI can be used to help prevent injuries by analyzing player performance data and identifying areas where a player may be at risk of injury. For example, AI algorithms can analyze data on a player’s throwing motion and identify areas where they may be putting too much stress on their arm. This information can be used by coaches to adjust a player’s training regimen and reduce their risk of injury.
5. Stolen bases: A system called “AI-Stealing” has been developed by the company Hawkeye Technologies in collaboration with the MLB. AI-Stealing uses machine learning algorithms to analyze datasets on a pitcher’s pickoff move, delivery time to home plate, and other factors that may affect a runner’s ability to steal a base. The system can provide real-time feedback to coaches and runners on the likelihood of a successful stolen base attempt, as well as tips on how to improve their technique.

AI is enabling coaches and scouts to make better decisions about player selection, training, and development by providing them with new insights into player performance. As providers of AI technology continues to evolve their offerings, it is likely that we will see even more sophisticated applications of AI in the world of baseball performance analysis in the future.

Although we may not see robot umpires in games soon, they are already being used to help train pitchers during bullpen sessions where the use of AI like Rhapsodo and Trackman are normal fixtures.

Pitch Tracking

AI is being used to track the trajectory and spin of pitches, which can provide valuable insights into a pitcher’s performance. Here are a few ways that AI is being used for pitch tracking:

1. Radar technology: Radar technology is widely used in professional baseball to track the speed of pitches. Pitch speed is an important metric for evaluating a pitcher’s performance, as it can indicate how difficult the pitch is for the batter to hit. Radar systems use radio waves to track the movement of the ball and calculate its speed. You see this when they show the StatCast data sponsored by Amazon’s AWS.
2. Machine learning algorithms: Machine learning algorithms are being used to analyze data from radar systems to identify patterns in the movement of the ball. For example, the TrackMan system uses machine learning algorithms to analyze data on the velocity, spin rate, and movement of each pitch. This information can be used by coaches and scouts to evaluate a pitcher’s performance and identify areas for improvement.
3. Spin rate analysis: Spin rate is another important metric for evaluating a pitcher’s performance. High spin rates can make pitches more difficult for batters to hit, while low spin rates can make them easier to hit. AI algorithms can be used to analyze data on spin rates and provide insights into a pitcher’s performance.
4. Trajectory analysis: AI can also be used to analyze the trajectory of pitches and provide insights into a pitcher’s performance. For example, AI algorithms can be used to analyze data on the movement of the ball, such as its horizontal and vertical movement, to provide insights into the effectiveness of different pitches.

AI is providing coaches and scouts with new insights into pitcher performance by analyzing data on pitch trajectory and spin. As AI technology continues to evolve, it is likely that we will see even more sophisticated applications of AI in the world of pitch tracking in the future. Managers used to watch innings, now it’s pitches, maybe soon it will be something like “effort”.

Fan Engagement

Here are a few ways that AI is being used to enhance the fan experience:

1. Personalized recommendations: AI is being used to provide personalized recommendations to fans based on their preferences and behavior. For example, the San Francisco Giants have introduced a system called “Oracle Park Pass,” which uses AI to provide personalized ticket recommendations to fans based on their interests and behavior. The system can also provide real-time updates on game scores, highlights, and other information that may be of interest to fans.
2. Chatbots: Chatbots are being used to provide fans with personalized customer service and support. For example, the MLB has introduced a chatbot called “MLBbot,” which allows fans to ask questions and get information about their favorite teams and players. The chatbot uses natural language processing (NLP) technology to understand fan requests and provide relevant information.
3. Virtual reality: Virtual reality (VR) is being used to provide fans with immersive experiences at baseball games. For example, the MLB has introduced a VR experience called “Home Run Derby VR,” which allows fans to experience the excitement of a home run derby from the comfort of their own home. The VR experience uses 360-degree video and audio to create a realistic and immersive experience for fans.
4. Social media engagement: AI is being used to analyze social media data to provide insights into fan behavior and preferences. For example, the MLB uses AI to analyze data from social media platforms to identify trending topics and engage with fans on social media. This information can be used to provide personalized recommendations to fans and enhance the overall fan experience.

AI is helping to enhance the fan experience by providing personalized recommendations, improving customer service, providing immersive experiences, and analyzing social media data to identify trending topics and engage with fans. As AI technology continues to evolve, it is likely that we will see even more sophisticated applications of AI in the world of fan engagement in the future.

In-Game Decision Making

Here are a few ways that AI is being used to help managers make better decisions during games:

1. Player tracking: AI is being used to track the movement and positioning of players during games. For example, the MLB’s Statcast system uses machine learning algorithms to analyze data on player performance, including pitch velocity, hitter exit velocity, and defensive positioning, to provide managers with insights into the game that they may not be able to see from the dugout. This information can be used to make better decisions about outfield player placement, substitutions, and strategy during games or even at-bats.
2. Pitch selection: AI is being used to help pitchers and catchers make better decisions about pitch selection during games. For example, the Astros have introduced a system called “Tunneling,” which uses machine learning algorithms to analyze data on pitch movement and trajectory to help pitchers and catchers select the best pitch for each situation. This information can be used to help pitchers and catchers outwit batters and gain an advantage during games.
3. Probability modeling: AI can be used to create probability models that help managers make better decisions about game strategy. For example, AI algorithms can be used to analyze data on player performance and historical game outcomes to predict the likelihood of different game scenarios. This information can be used by managers to make informed decisions about when to make substitutions, when to call for a bunt or a steal, and other game strategy decisions.
4. Umpire decision support: AI can be used to help umpires make better decisions about balls and strikes during games. For example, the Automated Ball-Strike System (ABS) uses machine learning algorithms to analyze data on pitch trajectory and ball location to provide real-time feedback to umpires about whether a pitch was a ball or a strike.

AI is helping baseball team managers make better decisions during games by providing insights into player performance, pitch selection, game strategy, and umpire decision making.

Testing Process

While the Atlantic League is not officially affiliated with Major League Baseball, it has served as a testing ground for new technologies and rule changes that are later adopted by MLB. In recent years, the Atlantic League has partnered with MLB to test a variety of new technologies, including robot umpires, pitch tracking systems, and AI-based player performance analysis tools. The use of these technologies in the Atlantic League has helped to refine them and make them more effective for use in MLB. The Atlantic League has also experimented with new rules aimed at improving the pace of play and increasing fan engagement, such as a rule that allows batters to “steal” first base and a rule that limits defensive shifts. Overall, the Atlantic League has played an important role in shaping the future of professional baseball by serving as a testing ground for new technologies and rule changes that have the potential to revolutionize the game.

In case you were wondering, the image at the top of this article was AI generated using Midjourney.