Data Science @WHOOP // Formerly Data @Pirates, Physiology @UF, Analytics @SyracuseU
Boston, MA
Joined November 2012
- Tweets2.7K
- Following541
- Followers766
- Likes865
Justin Perline retweeted
NEWS: The Pittsburgh Pirates are naming Justin Newman their new Director of Amateur Scouting. Newman has spent the last ten years with the Pirates. He has an heavy analyical background and served as the team's Director of Player Analysis this past year.
👇MORE BELOW👇
Kinda love this. You’d honestly get better information from the stadium biomechanics capture that can be compared 1-to-1 with that pitcher’s history, especially if this becomes a regular thing.
I have to believe something was lost in translation here. Maybe AI in the broadest sense but almost certain all these pitch calling models are your everyday machine learning kind
Breaking story on MLB's crackdown on generative in-game iPad apps making pitch and strategy suggestions: nytimes.com/athletic/7448900…
A few years ago I ran a quick analysis of team-level injured days over expected (from player-level predictions) and saw close to zero correlation in team rank year-over-year.
With @Britt_Ghiroli -- why do certain teams seem to have an injury problem in the minor leagues? We talked to GMs, trainers, coaches, and analysts to try and figure it out: nytimes.com/athletic/7330754…
My thoughts on this are already captured in my previous thread - ACWR is an outdated and mostly incorrect method for estimating injury risk xitter.cf/jperline/status/187496…
Nolan Ryan produced an incredible workload (5th all time in IP) and did so w/high velo. Managing and building workload remains far from optimized. What would attempting to a Ryan-like workload look like today? @maxengelbrekt, @hedgertronic and I explored: drivelinebaseball.com/2025/1…
As is the season, if anyone has questions about getting a job with an MLB team & the pros/cons of working in baseball vs. not feel free to reach out!
Not playing is certainly one way to reduce injuries. I haven't seen data that year-round play increases injury risk beyond just increasing exposures.
News: MLB is banning team officials from watching amateur players or collecting video and data on them for a monthslong period over the winter, saying year-round play “is putting young players at a dramatic risk of future injury.” Story free at ESPN: espn.com/mlb/story/_/id/4630…
This would be a fun data science project. A lot of different testable hypotheses in here
This is a really interesting 2 mins on QB height and 'seeing over the line'.
Purdy is 6'1 and says he basically can't see shit 40% of the time, and you're deducing the throw from the info you do have pre and post snap.
Short QBs I suspect struggle hard early because they're not comfortable with that at all yet. The sheer volume of throws they have to make on faith, based on the processing they did on the play.
I made an app if anyone wants to give it a try!
jperline.shinyapps.io/nation…
You can rank your favorite national parks and fill in a few other details about when you went, for how long, etc.
For now it only collects data but will eventually host fun analyses like consensus rankings
Nice job Cuse team 🍊
Mini life update!
Last week my team along with fellow classmates Dan Griffiths, Hunter Cordes, Jared Weber, and Josh Davis were announced as winners of the 2025 @Reds hackathon!
The prompt was to predict playing time for 2024. View snippets of our presentation below (1/2)
Justin Perline retweeted
Heart rate data using @WHOOP from my first ever big league spring training game.
4:35: manager walks out from dugout to make pitching change (142 bpm)
4:37: first pitch (175 bpm)
4:38: heart rate peaks (182 bpm)
4:40: out recorded, inning over (179 bpm)
Congrats to Josh Hejka (class of 2019) on his appearance for the Philadelphia Phillies in big league spring training! One batter, one out! @HopkinsSports @CentennialConf @hedgertronic
I was criticizing MLB’s injury report a couple of weeks ago and mentioned that I would provide some research that I think is actually helpful for those with access to injury data. Maybe long thread?
Another really cool field I’ve been inspired by here is motor control - there are coordination measurement and motor variability features that can be generated from biomechanics data. Here’s a recent one that describes a process for getting at coordination sciencedirect.com/science/ar…
