Portfolio

---

Coursework in R

• Random Forests and Experiments
• Logistic and Regularized Regression
• Splitting Data Sets and Linear Regression
• Loading files and Basic GGPlot

---

Projects

Big Data Bowl (coming soon)

Slide Deck

Code

Our submission to the 2022 NFL Big Data Bowl will include generating an ‘expected return yards’ metric from the moment the player catches the ball. The project takes player tracking data and uses variables such as kick length, hang time, distance, speed, and acceleration of the kickoff team to predict expected yards. How a returner performs relative to the expected yards will determine how efficient a return is.

---

Analyzing Competitive Imbalance Problem in Major League Baseball

This paper aims to identify why Major League Baseball has a competitive imbalance and economic inquality issue and how to fix it. A few potential solutions are identified but the preferred solution is introducing a salary cap. Although the MLBPA will never agree to this (hence the reason MLB is in the middle of a work stoppage), my paper discusses the implications of a salary cap and what it’s implementation would look like.

---

Predicting Starting Pitcher’s Market Value

Excel file

A baseball agent asked me how can we quantify in value/contract projections the premium for pitching at a certain stadium. After generating a market value on every 2022 free agent starting pitcher, park factors were used and adjusted to the player’s market value.

---

MLB Payroll and Success Correlation

In this project I do a brief study on the impact of team payroll on win percentage. As expected, a higher payroll typically leads to a higher winning percentage.

---

Other Projects in Progress