Page 19 of 19
Re: APBR-DraftExpress 2015 NBA Draft Project
Posted: Tue Aug 11, 2015 8:31 pm
by DSMok1
Crow wrote:So in general models do only so so immediately but tend to look better after a long time? 2002 was the worst draft for models? How about GMs? Would be nice to compare their performance that year and every year to the available models.
They have the actual draft order listed, which is what the GMs did.
It looks like the consensus is the best performing, well above the actual draft order every year.
Re: APBR-DraftExpress 2015 NBA Draft Project
Posted: Tue Aug 11, 2015 8:52 pm
by Crow
So they do, thanks. I missed it in the middle of the second line of the key. One of ten lines, not mentioned in graph title or in discussion to my quick read. Tiny on my phone screen, but it is there. My oversight.
Best twice, tied for best once (including consensus, Daniel, if I read right, so many shades of green and blue make it a bit hard), but all long ago.
Bettered by one or more model all other years. Worst twice. Not that impressive for full-time insiders with 6-7 digit research budgets and years of study into each draft class.
Re: APBR-DraftExpress 2015 NBA Draft Project
Posted: Wed Aug 12, 2015 6:30 am
by jessefischer33
While I without a doubt agree that the models perform better than GMs, one thing to keep in mind is that the models are all using "future" data to make these predictions. A more fair method to compare with GMs would be to only use prior years to make a particular years projections. It would be interesting to see how much this would change things. I imagine more recent years would be affected minimally whereas years further ago might see some notice me change from smaller data sets.
Related: I think in some ways this could actually benefit models to incorporate recency more (to pick up playing style changes over the year) - for example 3s in the 90s are likely a worse predictor than in recent years. I may attempt to incorporate this a bit in my next iteration of model improvements.
Re: APBR-DraftExpress 2015 NBA Draft Project
Posted: Wed Aug 12, 2015 1:08 pm
by DSMok1
jessefischer33 wrote:While I without a doubt agree that the models perform better than GMs, one thing to keep in mind is that the models are all using "future" data to make these predictions. A more fair method to compare with GMs would be to only use prior years to make a particular years projections. It would be interesting to see how much this would change things. I imagine more recent years would be affected minimally whereas years further ago might see some notice me change from smaller data sets.
Related: I think in some ways this could actually benefit models to incorporate recency more (to pick up playing style changes over the year) - for example 3s in the 90s are likely a worse predictor than in recent years. I may attempt to incorporate this a bit in my next iteration of model improvements.
Very good point. We've got future data involved here, and it is also likely that the draft models were trained on some of the years shown here--so it is an "in sample" prediction.
Re: APBR-DraftExpress 2015 NBA Draft Project
Posted: Thu Aug 13, 2015 10:10 pm
by Crow
In sample colors current findings. But GMs had access to non public information (workouts, interviews, medicals) and not very publically known data (all games, high school, aau, showcases, practices, off court) and had the ability to influence performance via coaches (minutes, situations, shots, when removed, etc.) So it is not a fair fight both ways.
Re: APBR-DraftExpress 2015 NBA Draft Project
Posted: Tue Nov 03, 2015 2:47 am
by ampersand5
TJ McConnell is looking like he can play in the NBA.
Re: APBR-DraftExpress 2015 NBA Draft Project
Posted: Tue Nov 03, 2015 3:53 pm
by Statman
ampersand5 wrote:TJ McConnell is looking like he can play in the NBA.
Yep. My quotes about him on twitter just after the draft:
Code: Select all
TJ McConnell also NEEDS to be drafted, he's more Crafty or Dellavedova-y than Craft or Dellavedova. Plus he's a "true" PG w/ the floor dives
after picked up by Sixers for Summer League:
Wouldn't be surprised at all if he's their starting PG much of the year.
He was 27th in my draft model.
http://hoopsnerd.com/?page_id=823
Re: APBR-DraftExpress 2015 NBA Draft Project
Posted: Sat Sep 27, 2025 6:25 am
by Crow
Stumbled back to this thread.
Scrolled thru it.
Might be interesting to evaluate performance after 10 years.
Might be interesting to hear how participants do things the same or differently.
Notable how much interaction occured back then.
I don't know if I'll do a detailed analysis of the thread. May be influenced by any signs of interest from others.
Re: APBR-DraftExpress 2015 NBA Draft Project
Posted: Sat Sep 27, 2025 3:26 pm
by Crow
3 of top 10 GM draft picks in top 10 career BPM to date. 5 taken 20th or later.
6 bigs, 4 guards, no wings. 4 of top 5 were bigs.
Switch to VORP, only 1 new guy enters top 10.
Model consensus top 10 called 6 of 10 best on career BPM.
Compared to model consensus, GMs didn't pick Wright, Turner, Looney or Jones in top 10.
Both failed to have Booker in top 10.
GMs had Porzingis. I believe internationals were excluded in the models.
Neither had Harrell or Nance.
They match perfectly on 1 - 3 and were right on Towns, moderately off on Russell, way off on Okafor.
Models had Winslow 4th, GMs 10th. 30th on career BPM. Horrible shooting from almost every distance. Presaged by college shooting including FT%.
DX articles no longer present on DX.
Individual model performances not yet checked or ranked after 10 years. Jesse Fischer had data / ranks after a couple of years.