Can Statcast Data Improve MLB Player Performance Predictions? — Beating Marcel with LightGBM

📰 Dev.to · YMori

Learn how to improve MLB player performance predictions by 12.1% for batters and 4.0% for pitchers using Statcast data and LightGBM

intermediate Published 6 Mar 2026
Action Steps
  1. Collect MLB Statcast tracking data for exit velocity, barrel rate, Whiff%, and Stuff+
  2. Preprocess the data for use in a machine learning model
  3. Train a LightGBM model using the preprocessed data to predict player performance
  4. Compare the results to the Marcel projection system
  5. Evaluate and refine the model to achieve the best possible predictions
Who Needs to Know This

Data scientists and analysts on a sports team can benefit from this approach to gain a competitive edge in predicting player performance

Key Insight

💡 Statcast data can significantly improve the accuracy of MLB player performance predictions when used with a suitable machine learning model like LightGBM

Share This
🏟️ Boost MLB player performance predictions by 12.1% for batters and 4.0% for pitchers with Statcast data and LightGBM! 📈

Key Takeaways

Learn how to improve MLB player performance predictions by 12.1% for batters and 4.0% for pitchers using Statcast data and LightGBM

Full Article

I tried to beat the Marcel projection system using MLB Statcast tracking data (exit velocity, barrel rate, Whiff%, Stuff+). Here's what happened: +12.1% improvement for batters, +4.0% for pitchers.
Read full article → ← Back to Reads

Related Videos

Build an AI Voice Assistant with Python | Listen, Think & Speak | Tamil | Karthik's Show
Build an AI Voice Assistant with Python | Listen, Think & Speak | Tamil | Karthik's Show
Karthik's Show
AI & Machine Learning Course Review by Tandeep Sandhu, Solutions Directior
AI & Machine Learning Course Review by Tandeep Sandhu, Solutions Directior
Great Learning
William Tyler Shares His Journey in UT Austin’s AI & ML Program
William Tyler Shares His Journey in UT Austin’s AI & ML Program
Great Learning
AI for Leaders: Usha Boddapu’s Journey through UT Austin’s PGP AIFL Program | Great Learning
AI for Leaders: Usha Boddapu’s Journey through UT Austin’s PGP AIFL Program | Great Learning
Great Learning
The Adam Optimizer is Just Momentum + RMSProp
The Adam Optimizer is Just Momentum + RMSProp
DataMListic
How to start learning AI | Complete AI Learning Path | Roadmap For Beginners (With No Background)
How to start learning AI | Complete AI Learning Path | Roadmap For Beginners (With No Background)
Career Talk