Recruiting prediction model....

#3
#3
Something that is interesting is, look how many players we are on the list of. Quite a few. Looks to me to be more than Southern Cal.
 
#7
#7
I don't like how it says we are going to lose David Oku (Nebraska) and Eric Gordon (Oklahoma).
 
#9
#9
Chris Bonds and Terry Shankle, predicted school TN?...first I have heard on that.
 
Last edited:
#12
#12
there are a two things that jump out to me very early...

Patrick Patterson:

30.7% to Ole Miss
23.9 to Alabama
18.4 to Southern Miss
17.1 to TN
6.7 to Miss state

MSU is probably his leader with Alabama battling and TN is more in the hunt than Southern Miss. that one's really scrambled.

it picked Bryce Brown going to Missouri.

they're a Big-12 spread---why would he want to run in that offense?
 
Last edited:
#15
#15
Tennessee Jack said:
there are a two things that jump out to me very early...

Patrick Patterson:

30.7% to Ole Miss
23.9 to Alabama
18.4 to Southern Miss
17.1 to TN
6.7 to Miss state

MSU is probably his leader with Alabama battling and TN is more in the hunt than Southern Miss. that one's really scrambled.

it picked Bryce Brown going to Missouri.

they're a Big-12 spread---why would he want to run in that offense?
Click to expand...
You mean Ole Miss is probably his leader.

Also scroll down and take a good look at the players that the system missed on. Most of them are reconsidering their decision and will likely end up elsewhere. It will be neat to see the % after signing day.
 
#16
#16
Bonds and Shankle would be awesome pickups, haven't heard much on them though.

Rivals says shankle visited way back in Sep.
 
#17
#17
All I know is that its track record so far for Tennessee is really bad. That is probably because I remember distance being a big factor when this was linked to in the past...and with Tennessee nationally recruiting, they will miss Tennessee more than some others.
 
#18
#18
This is all based on regression analysis. To say that it's "way off" on one person or another is woefully naive. The whole purpose of this is to show that behavior can be predicted fairly accurately based on the number of factors that one includes in the analysis. The greater number of factors included into the model correlates with greater accuracy in its prediction. Rather than picking out individual recruits on which it's "way off," I think that it's far more interesting to note that something as complicated as recruiting can be predicted at all...much less with 75% success.
 
#19
#19
volinathens said:
This is all based on regression analysis. To say that it's "way off" on one person or another is woefully naive. The whole purpose of this is to show that behavior can be predicted fairly accurately based on the number of factors that one includes in the analysis. The greater number of factors included into the model correlates with greater accuracy in its prediction. Rather than picking out individual recruits on which it's "way off," I think that it's far more interesting to note that something as complicated as recruiting can be predicted at all...much less with 75% success.
Click to expand...

Perhaps I misunderstand what you are saying, but I don't think that woefully naive is the correct terminology at all. The predictions is trained through various (large) training sets to establish the weighting for the regression. However, certain school could go about recruiting differently - and thus not correlate well with the mean - or a certain recruit could look for something very different than the typical recruit, and thus not correlate well. Of course the prediction can be "way off" for some people/schools and not for others, depending on how well their priorities correlate with the dominant priorities of other recruits.
 
#20
#20
Don't know if I agree with Marlon Brown's predictions: Tennessee 22.6%, Ole Miss 17.9%, Florida 17.6%, Ohio State 16.5%, and THEN Georgia at 15.7%....
 
#21
#21
So type of system and type of player are never factored into this, right? I saw nothing to suggest that in this list. It's all need-based on the class and the distance between the recruit and the school.

That would explain why Bryce Brown (pro-style RB) is projected to play in a spread offense at Mizz and why Aaron Murray was picked to play at UF and not UGA.

Sabanocchio said:
You mean Ole Miss is probably his leader.
Click to expand...

right, that's what I meant... :good!:

I was thinking Mullen's arrival had shuffled his list for
some reason. :fool:
 
#22
#22
I think everyone is reading this wrong...it's simple...

It works 75% of the time, everytime.
 
#23
#23
Another thing I noticed is that they were only wrong on one guy who they thought would commit to Tennessee (C. Bonds, Bama)... and the best part is that out of the ones they got wrong, four guys committed to us who they thought wouldn't (David Oku, Jerod Askew, Eric Gordon, and DJ Hunter... who is irrelevant now, but still...)
 
#24
#24
423VOL said:
Don't know if I agree with Marlon Brown's predictions: Tennessee 22.6%, Ole Miss 17.9%, Florida 17.6%, Ohio State 16.5%, and THEN Georgia at 15.7%....
Click to expand...

I think I'm starting to get the hang of this...

The predictions are based on distance/recruiting class needs and other factors, it has nothing to do with the rumblings out on the recruiting trails.

That's why some of these lists are so puzzling. The list doesn't reflect any recent events which would factor into the projection. That's why some are very accurate and some are very puzzling.
 
New posts
You must log in or register to reply here.

VN Store



Back
Top