Golf data analyst. Building a public PGA prediction model. Created Rainy Day Golf.
Westfield, IN
Joined April 2009
- Tweets3.5K
- Following493
- Followers145
- Likes484
Pinned Tweet
For those new, I built a golf prediction model. Here's what it does, how it works, and what it's actually gotten right. 🧵
a year ago I built a golf career sim, got a random spike of traffic, then walked away from the project completely for months. checked the numbers this week almost as a joke. 6,700 people played anyway. the demo still said "Season: 2024." I'm that guy.
I love how we're already getting @TheMasters takes. I’m trying to keep mine boring and focus on who’s driving and approaching well right now, and how that lines up with what #Augusta tends to reward. Narratives are fun but the dispersion chart usually wins.
Cameron Young wins The Players. He was #8 in my model this week. 🎯
The model doesn’t care about vibes, just strokes gained + current form.
Next up: @ValsparChamp everything leading up to the model for the #Masters.
Follow along!
Weekly Golf Model Note: 57 backtests, 23.2% Top‑10 hit rate. After 36 holes at #ThePlayers, the board is packed, so Saturday volatility matters more than name value. What’s the one skill you think separates contenders on moving day? Can Scottie keep it up?
Saturday at TPC Sawgrass: I’m comparing my model’s top 10 to the live leaderboard and sharing what’s holding up. Quick notes coming later today for #THEPLAYERS
Golf + data science project: my model has processed 57 tournaments so far, and I’m sharing what it’s learning as the @THEPLAYERS unfolds.
This week, one of my biggest movers was Jake Knapp and he withdrew sick 15 minutes before his tee time.
That's #golf. Follow along! 🏌️
It runs 10,000 simulated tourneys and gives every player a win %, top 10 % and top 20%. Across 55 backtested tourneys:
- Top-10 accuracy: 21.8%
- Top-20 accuracy: 35.9%
Picked the winner outright 8 times.
Not perfect, but it's finding signal!
The biggest question is how much should last week matter vs. last year? I've been running it conservative on purpose. Gotta set a baseline first.
It all starts with strokes gained. I've intentionally kept some variables out from this experiment like course fit so it only focuses on baseline stats + current form.
After 2 rounds at Bay Hill, 3 of my model's top 5 picks are inside the top 10.
Morikawa: ranked #4 → T3 (-7) 🎯 Henley: ranked #5 → T7 (-5) 🎯 McIlroy: ranked #3 → T9 (-4) 🎯
Scheffler is T15
Berger still leads. He wasn't in my top 15. 🤷
#ArnoldPalmerInvitational #PGATour
My model moved Jake Knapp from #19 → #4 this week.
He withdrew 15 minutes before his tee time due to illness.
Can't model health. 🤦
#ArnoldPalmerInvitational #PGATour
Matt Strobel retweeted
250k followers!
As thanks, I’m going to giveaway tickets to the MAJOR 😂 the Players Championship! plus some signed @range_finance hats and some of my personal @Titleist gear.
Must be a follower. Comment, like, retweet to enter.
