Ryan Gunther

Now we see why I maxed out at the collegiate level 🤣 just 11 big league homers were hit at or below this bat speed in 2025

(Me, today, measured by blast motion)

Hire me!

- Master's degree in statistics (thesis on hitting biomechanics)
- Experienced in computer vision, R, SQL, Python
- interned with 2 Indy ball teams, in pitch data (2024) & automation (2025)
- former collegiate player
- worked 3.5 years in finance/contract structuring
- Bachelors in finance

In today's episode of unintuitive things I'm excited about - Isomap finds Ernie Clement and Ernie Clement's mirrored swing almost identical after dimension reduction!

This means that if lefties continue to have higher transformation scores than righties, I've found something significant!

I miss Joey Votto!

YouTube video by Jeff Nippard The Science Behind Sam Sulek’s Training

reminds me of this jeff nippard video: www.youtube.com/watch?v=ml5u...

Where did you go? I am heading there next May!

Yeah, this was super cool news when announced

I'm back to inquire if the "Ryan G" who finished 10th could be mine. (I am a Ryan G, the link you provided is a filthy generic
Ryan)

Is there any way to figure out, given I don't remember any of my answers? Unlike me to not have that saved, but I've searched high and low and found nothing

This is excellent, is this available to the public on FG? I saw your article today but haven’t read it yet

Very good, thanks. My above post was more about the post estimation of the body (white dots on knees, shoulders, ankles, etc) but I think this info is super useful for Stephen’s work and probably mine at some point too

Just saw your other post referencing a streamlit app, got it now!

Not sure if this was a reply to me or not, but I remember asking Tom Tango about this, this visualization is essentially “one typical swing” for a hitter but won’t give you swing-by-swing variation

For sure. The open biomechanics project (OBP) is super interesting and is full of pitch deliveries as well, which I know is much more your wheelhouse than mine

To sum it up, to get to a different place, one must travel a different route!

The purple dots ends up reaching a max "right side" (in this clip) location about 10cm/4 inches further right than red does

I should disclose that this is an anonymized hitter from the openbiomechanics project (pro/college/HS), and not an MLB hitter, but the concepts should hold at all levels

Here are two swings, same hitter, overlaid on each other, one makes contact with a ball in Zone 10, the other, Zone 11 (up+out vs up+in)

Barrels (red/purple) tunnel each other like 2 pitches tunnelling each other. But from overhead view you can see that they break off pretty early in the motion

with that being said, I think there's a case for the barrel on an inside pitch never overlapping with the barrel's location on the early part of an outside pitch. I can dive deeper into this if you think I could help you

If I've misinterpreted anything please correct me

Ok, I agree more with your updates than the initial post. If I have interpreted the plots correctly, that is the barrel's location throughout a hypothetical swing

If my understanding is correct, the first plot doesn't natural at all. The quote posts of Ohtani, Freeman, and Kwan look a lot better

definitely will read this tomorrow since it's in my wheelhouse!

More on the model tomorrow once it's not 2am anymore. First thing that jumps out here is Del Castillo getting to a super twitchy / athletic position in these early frames and then letting his body rotate and release out of it

Exciting new updates in baseball computer vision - I generated this (and many other clips like it) completely automatically through a pipeline I've built

Here's Adrian Del Castillo turning 96 above the zone into a gap double. Auto color-coded too, so the denser centers hold more weight in my model

Yeah, I deserved that 🤣 makes sense, given velo plummets in that middle zone too

Fun topic.

For the last graph, I’m assuming “run value” is run value for hitter? I.e. lower on the y axis is better for the pitcher? Or do I have that backwards

single game WAR is not a thing. Nonetheless, I'd have to imagine 2 home runs, 2 doubles, 5 walks in 9 PA, even with a CS and the DH penalty, would be >1 WAR in a single game

goodnight. no need to watch game 4 tomorrow, it already happened in the second half of game 3

Biebs getting warm makes me think Springer could be hurt bad enough that Toronto knows they’ll have to take him off their roster. Yariel or Berrios (is he healthy?) could start game 4 if Bieber comes in tonight?

Jays fan. Felt.

Putting the pieces together in my computer vision project - I've now taken Bogaerts swing footage, programmed the ability to automatically drill out "donut holes" i.e. the section between XB's arms at contact, then colour code so the centers of the data hold more weight

No matter how I tune this, tree-based models only care to split for runners advancing from 2B on possible sac flies. From 3B it's pretty simple

Hangtime doesn't matter. Neither does OF initial positioning, launch angle, OF arms, runner speed, or where the ball's hit. If it's >260ft, you're scoring

Thanks, I didn’t realize FG and BRef had different win probability models. The most granular I can see on BRef is whole numbers rounded (Jays 37% to 77%), no decimals, so I went to FG for a closer look.

I didn’t think counts were a factor in WPA, thanks for confirming that!

@tangotiger.com maybe you know…have I missed something here? I see FanGraphs having the Jays win prob before the play as 36.7, after 77.5. Difference is 40.8, multiply by 0.500 (coefficient for CS G7) and should get 20.4. BBREF has the cWPA as 19.73%. Are they factoring in a 1-0 count?