A Little About Me

Hi y'all! Welcome to the first entry of my blog. I'll be using this space to share some of the work that I want to work on that isn't too formal. Surprise, surprise...it's probably going to be pretty Bayesian-coded haha!

About Me

Currently, I am a recent graduate of UC San Diego where I studied data science. During my time at UC San Diego, I was fortunate enough to have interned for the school's d1 baseball team as a data scientist. I worked primarily with the pitching team, in which I'd help out the pitching coach by developing tools/analyses for player evaluation purposes. I worked on some other stuff too like a pitch classification pipeline and a cloud data pipeline - which made life easier for everyone.

My career interests are pretty much bound to sports analytics - but in particular baseball! I've not only had the pleasure of working within a college baseball organization, work on baseball projects for classes, but I've also gotten to go to the SABR Analytics Conference twice (in 2025 and 2026) - thank you Tyrone Brooks!

There are, of course, a variety of positions within a baseball front office, however, given my technical nature, my career goal is to work as a data scientist/quantitative analyst/r&d analyst/baseball analyst - whatever you want to call it haha - and work on creating baseball solutions for baseball problems. I'm also more interested in the research side of things - such as using probabilistic modeling for long-term problems like player projections!

In my free time, I enjoy listening to music (love The Strokes and all things indie), watching movies (anything Wes Anderson, Quentin Tarantino, or Tim Burton), and playing video games (MLB the Show Franchise fein).

My Work

I've already touched on some of the stuff I worked on for the school team, so I'll touch on other projects I worked on that I'm proud of - and that also reflect my interest in baseball.

To give a bit of context as to the nature of my projects: for the past year or so, I've become really interested in Bayesian statistics. I think how I came to be is a question that I'm not even really sure the answer to haha. My guess is that I watched a youtube video titled "the hidden side of statistics", or something of the nature, and found out that it had applications in baseball that looked cool. I also came to realize that Bayesian statistics is by no means an easy concept to grasp at first.

Which leads to the first baseball/Bayesian project I did, which was: Bayesball in the Outfield: Quantifying Defensive Aggression With a Bayesian Hierarchical Model, as a part of the 2025 SMT Data Challenge. This project was my first time ever doing any form of Bayesian modeling - and it is apparent when looking at the model architecture and specifications. Basically, using spatiotemporal player- and ball-tracking data, I tried to infer the probability that any given outfielder would be "aggressive" on a ball in-play to the outfield. This project gave me a good amount of practice with working with tracking data - also good refreshers in trigonometry and calculus haha - and just gave me a better idea as to how Bayesian models work. I was also fortunate enough to have been recognized as an honorable mention finalist in the whole competition!

The second project that I did was a class project I did for my graduate astrostatistics course, which was: Probabilistic Modeling of True Hitting Talent in Major League Baseball. I realized in interviews with MLB teams that I would say I'm interested in the player projections side of baseball, yet, at those points in time, I had zero projects as to where I did just that. The grad class covered Bayesian statistics, so I learned about hierarchical Bayes, Gaussian processes, and different forms of posterior estimation (i.e., MCMC and VI). So this project was basically just applying all of that to create a more complex MARCEL - since I couldn't do an actual astrophysics final project for the class since I am by no means a grad astrophysics student haha.

This is all I have up til this point where I applied Bayesian statistics within a baseball setting, but there will be, of course, more to come eventually!

My Blog

This blog is meant to journal any progress I make in becoming a better data scientist - and Bayesian. To start off the technical content of this blog, I'm going to be reading the chapters of BDA3 throughout the summer, summarize what I learned in each chapter, and implement what I learned within a baseball context - naturally.

Thank you for reading and I hope you'll enjoy the content that I'll be putting out!

Best, Diego