NBA Draft | Jets | Knicks | Mets | Draft model results here https://xitter.cf/t.co/e0CgL5MfIm

Joined January 2021
Still working on the UI but if you are curious of my epm models results they are linked here. Please ask any metholodogy questions or anything. nba-epm-projections.streamli…
9
4
3
21
13,049
I added a backtest feature if anyone is curious what old results looked like
Always thought there was lots of value in reviewing any database, analyzing it hard and creatively. By the creator and / or users. At time permits and interest exists.
1
3
357
Still fiddling with it some of it looks funky
16
Top 10 second year player 5 year projection in my model
2
2
4
929
they’re coming.
17
110
20
2,061
47,265
Fiddling with a spread picks model using my player projections. Have lost two picks this season so far (Orlando and Bucks spread). Don’t expect to keep up this rate but damn
2
3
201
Cleveland +3.5 tn and slight lean to okc spread tn
1
1
88
Bump
Ty Jerome will average more ppg than anyone on the sixers
4
281
Don't know how much I believe this but I think the Magic are going to win a playoff series
1
104
Choosing to keep Miller over Lamelo ok
1
1
5
287
I would've just done what I could to keep both personally, losing White if you have to
56
Ty Jerome will average more ppg than anyone on the sixers
1
1
1
576
Paolo’s future is very underrated by the nerds
1
93
Cleveland up a couple wins cause Watson and Wolves like one cause Kuminga. Rest are my picks going into the season
Locking it in. Had to make some tough calls with play time but I tried my best. If curious why a team is low please ask
2
1
6
1,229
*bad for Charlotte
The Lamelo trade is going to look obviously bad like 5 games in
4
16
1,313
The Lamelo trade is going to look obviously bad like 5 games in
38
17
8
618
105,260
I think the Wolves got a great deal I should’ve specified
161
13,295
Ausar Thompson: • 98th% turnover generation • 94th% defensive shot selection • 89th% offensive rebounds +3.82 ARC per 100 possessions Curry: 31st pct in those decomps, but 100th in offensive conversion ARC +5.79: 50% more impact per possession Offensive Conversion is law.
4
19
4
121
10,751
Contemporary all-in-one impact metrics often regress box score actions onto RAPM to find their weights. A fitted model can give a steal about 3 times the value of a point scored leaving us with an opaque number that can't be decomposed into how or the degree they affect the game why not just count em up? Introducing ARC v3 An Expected Box Value Prior RAPM (EBV RAPM) That aims to quantify impact using possession by possession accounting 🧵
epv rapm is the final boss
8
31
10
156
15,326