• 

  Confusion Matrix

• 

  EDA1

• 

  EDA2

• 

  EDA3

• 

  EDA4

• 

• 

• 

• 

• 

• 

• 

• 

• 

  EDA5

• 

  Correlation Matrix

• 

  Feature Importance

• 

  PDP

MLB Travel Impact Analysis Project

Inspiration

The project was inspired by the fascinating world of sports analytics. The aim was to explore the lesser-studied aspect of how travel schedules affect MLB teams' performance, blending the thrill of baseball with the precision of data science.

What I Learned

This journey deepened my understanding of data analysis and machine learning. I learned the intricacies of handling large datasets, the importance of feature engineering, and the power of machine learning models, particularly XGBoost, in deriving meaningful insights from data.

How I Built It

The process involved:

• Gathering comprehensive MLB game data.
• Conducting thorough data cleaning and preprocessing.
• Feature engineering with a focus on travel aspects like distances and rest periods.
• Implementing and tuning machine learning models to analyze the impact of travel on performance.

Challenges Faced

The main challenges were:

1. Acquiring accurate location information data to assess travel distances and patterns.
2. Choosing and tuning the appropriate machine learning model to effectively capture the complexities of the data.

Conclusion

This project was a perfect amalgamation of my passion for sports and data science. It not only provided valuable insights into the effects of travel on MLB teams but also enhanced my skills in data analytics and machine learning.

Built With

• python