Author Archive

Modeling the Effect of Deadening the Baseball

Much has been made of the “juiced ball era” which we currently inhabit. Decreased drag on the ball along with an increase in-ball bounciness means that fly balls are carrying further, rewarding hitters with more home runs than ever before. This change has coincided with increases in strikeout rates which can be partially explained by pitchers throwing harder, but also may be due to more hitters selling out for a home run. There are now fewer balls in play than ever before, and many fans no longer enjoy this Three True Outcomes style of baseball.

Deadening the ball is a proposed solution to ballooning home run rates. Introducing a deadened ball along with measures to limit the dominance of pitchers (such as shrinking the strike zone) could increase the number of balls in play, improving the aesthetic value of baseball for many viewers as discussed on this site in a recent article. But what would baseball with a deadened ball actually look like? How much would the ball have to be deadened to return home run rates to those seen in past years? Would deadening the ball disincentivize strikeouts more strongly than the juiced ball? Which hitters would be the biggest winners and losers in a season with a deadened ball?

I aim to investigate all these questions in this article, so without further ado, let’s dive right in. Read the rest of this entry »

PitchingBot: Using Machine Learning To Understand What Makes a Good Pitch

People have always been looking to understand what makes a good pitch. With advances in pitch tracking technology and computing power, we can begin to use large amounts of data to answer this question more definitively. I’ve created a model called PitchingBot which uses machine learning to try and find what makes a good pitch.

Machine learning describes a general class of algorithms that are very flexible and “learn” patterns from large amounts of data. This means I don’t have to tell PitchingBot what I think a good pitch is, but instead I can give it a load of pitches (and the results of those pitches) and it will train itself to recognize a pitch that gives good results.

I intend to investigate a couple of key questions:

Does PitchingBot reach the same conclusions as conventional wisdom about what makes a good pitch?

Naively, I would expect a good pitch to have the following qualities: high velocity, plenty of movement, and good location in the corner of the strike zone. I will look at whether these are true for PitchingBot and how the definition of a good pitch changes with the ball/strike count.

Can we meaningfully compare and evaluate pitchers using PitchingBot?

Are the pitchers who are best according to PitchingBot those who get the best results? PitchingBot isn’t very useful if it does not agree with real pitcher performance. Read the rest of this entry »