23MAY2022 SNA/SNFO BOARD

[Maze_soba]

I'd definitely be interested in testing out my scores! They're underneath my posts. My low GPA is what worries most. Do you need more info?

Just need age and gender!

 

[carviator]

Just need age and gender!

29 M

 

[exNavyOffRec]

Hey y’all, I had too much time on my hands so I tried making an ML model of predicting SNA selection this afternoon.

It currently predicts Y/N with a 93% accuracy and I can try your scores through it if you want.

A couple of huge caveats here with the data:

• The quality of training data is pretty shit. I could only find 3ish spreadsheets easily on the AW forums, and was too lazy to go and find others.
• The “waivers” column seems to be a relatively recent addition, so it doesn’t really exist in the previous data. That said, accuracy didn’t improve when I discarded
• There is a pretty big bias towards “yes” because only the die-hards pilot wannabes post on this forum/spreadsheets and those that do are generally pretty likely to get yes’s. There is a surprising lack of prorec-N’s in the sheets I looked at.
• The selection yes/no is purely based off of SNA applicants. I didn’t include NFO because that was too much work and it seems you’re pretty likely to get in if you select NFO as your primary.
• I only had 150ish rows of data from the sheets I found, so I duplicated it on the assumption that the spread of applicant stats is relatively similar across boards, in order to get more training data. So, the existing biases are doubled.
• Didn’t include college major b/c I didnt' want to deal with it.
• This is strictly from the spreadsheet data, so it’s not reflecting the “whole person” concept with stuff that can’t be quantified. <- biggest caveat

So with those rather large caveats out of the way, here are some observations:

• Age IS unsurprising a big factor. Curiously, there’s a dip between 27-29, but I think that’s mostly a dataset issue.
• PFAR is the next best predictor
• OAR and GPA are weighted pretty similarly, as is AQR
• Interestingly, the FOFAR is a better predictor than Flight experience - meaning it can be said with pretty good confidence that flight exp doesn’t really matter.
• Prior service and sex are also negligible.

Next steps: if any of you guys and gals have extra time, it would be interesting to build out a better dataset together. That means finding the past board spreadsheets, cleaning it, and putting it into this model to train it better. That would yield better results, and I might be able to make a webapp so ppl can look up their own scores.

Using the model, I tried predicting my own prob of prorec-Y and got a Yes with 96%. LMK if you want me to try putting your scores into it and seeing what comes out. Caveats blah blah blah.

The model itself:

View attachment 34200

Trying my own scores
View attachment 34201

one thing to consider on that waiver column is sometimes people put "yes" but it is a medical waiver and the board doesn't deal with medical.

 

[smpl_dude]

Hey y’all, I had too much time on my hands so I tried making an ML model of predicting SNA selection this afternoon.

It currently predicts Y/N with a 93% accuracy and I can try your scores through it if you want.

A couple of huge caveats here with the data:

• The quality of training data is pretty shit. I could only find 3ish spreadsheets easily on the AW forums, and was too lazy to go and find others.
• The “waivers” column seems to be a relatively recent addition, so it doesn’t really exist in the previous data. That said, accuracy didn’t improve when I discarded
• There is a pretty big bias towards “yes” because only the die-hards pilot wannabes post on this forum/spreadsheets and those that do are generally pretty likely to get yes’s. There is a surprising lack of prorec-N’s in the sheets I looked at.
• The selection yes/no is purely based off of SNA applicants. I didn’t include NFO because that was too much work and it seems you’re pretty likely to get in if you select NFO as your primary.
• I only had 150ish rows of data from the sheets I found, so I duplicated it on the assumption that the spread of applicant stats is relatively similar across boards, in order to get more training data. So, the existing biases are doubled.
• Didn’t include college major b/c I didnt' want to deal with it.
• This is strictly from the spreadsheet data, so it’s not reflecting the “whole person” concept with stuff that can’t be quantified. <- biggest caveat

So with those rather large caveats out of the way, here are some observations:

• Age IS unsurprising a big factor. Curiously, there’s a dip between 27-29, but I think that’s mostly a dataset issue.
• PFAR is the next best predictor
• OAR and GPA are weighted pretty similarly, as is AQR
• Interestingly, the FOFAR is a better predictor than Flight experience - meaning it can be said with pretty good confidence that flight exp doesn’t really matter.
• Prior service and sex are also negligible.

Next steps: if any of you guys and gals have extra time, it would be interesting to build out a better dataset together. That means finding the past board spreadsheets, cleaning it, and putting it into this model to train it better. That would yield better results, and I might be able to make a webapp so ppl can look up their own scores.

Using the model, I tried predicting my own prob of prorec-Y and got a Yes with 96%. LMK if you want me to try putting your scores into it and seeing what comes out. Caveats blah blah blah.

The model itself:

View attachment 34200

Trying my own scores
View attachment 34201

That's pretty neat. What did you make it with? Also, you got a link to it?

 

[Maze_soba]

29 M

Yes with 93% confidence! You've got killer scores though, and fall into the weird age bias part of 27-29 so I think it's much higher in reality.

one thing to consider on that waiver column is sometimes people put "yes" but it is a medical waiver and the board doesn't deal with medical.

True, so I guess omitting it is the better move.

That's pretty neat. What did you make it with? Also, you got a link to it?

I made it with AWS's new Sagemaker Canvas thing! I tried sharing the model, but can't build the standard model required because I have less than 500 rows of data, unfortunately. So it would help if we built a better dataset. I see that you're a CS guy so you're probably better at this stuff than I am haha.

 

[carviator]

Yes with 93% confidence! You've got killer scores though, and fall into the weird age bias part of 27-29 so I think it's much higher in reality.
View attachment 34202


True, so I guess omitting it is the better move.


I made it with AWS's new Sagemaker Canvas thing! I tried sharing the model, but can't build the standard model required because I have less than 500 rows of data, unfortunately. So it would help if we built a better dataset. I see that you're a CS guy so you're probably better at this stuff than I am haha.

Nice thanks for the confidence boost lol. Just hoping spots are open for fy23

 

[Jacksa71]

You would need to do a commissioning physical through your medical, the info should be in the 1420

Do you know whether or not the medical section should be in a separate PDF from the application package? I have gotten mixed answers that it should be in the same PDF file, and others say make it separate.

 

[exNavyOffRec]

Do you know whether or not the medical section should be in a separate PDF from the application package? I have gotten mixed answers that it should be in the same PDF file, and others say make it separate.

If it sent together then the processors will need to divide it up as medical goes to N3M and the professional part goes to the board, communicate with the NRC processors though to see exactly how they want it.

 

[Jacksa71]

If it sent together then the processors will need to divide it up as medical goes to N3M and the professional part goes to the board, communicate with the NRC processors though to see exactly how they want it.

Thanks.

 

[SE_53]

Yes with 93% confidence! You've got killer scores though, and fall into the weird age bias part of 27-29 so I think it's much higher in reality.
View attachment 34202


True, so I guess omitting it is the better move.


I made it with AWS's new Sagemaker Canvas thing! I tried sharing the model, but can't build the standard model required because I have less than 500 rows of data, unfortunately. So it would help if we built a better dataset. I see that you're a CS guy so you're probably better at this stuff than I am haha.

If you go the the Nov board spread sheet there is the at board list in a different tab with everybody's scores from the board. You can cross check those with who was selected on the official release document to get some more data points if you haven't done that already. 300+ applicants total on the board. ?‍♂️

 

[Gliderpilot321]

Hey everyone! Looking at putting in my application in for the May 2022 board. I have studied for the ASTB. I’m a current flight instructor and graduated last May of 2021.

My main question for everyone applying is two recruiters have told me the May 2022 board may end up cancelling. Has anyone heard about this? I’ve tried to search it but have not found anything. Just looking for some guidance. Thanks!

 

[Madz91199]

Since I can finally reply to things now; just wanted to say that I am also applying for this board and am hella nervous and excited at the same time. I will be retaking the ASTB on the 7th, so if anyone has any advice or tips that they thought worked well for them, I will gladly accept them.

 

[Madz91199]

Hey everyone! Looking at putting in my application in for the May 2022 board. I have studied for the ASTB. I’m a current flight instructor and graduated last May of 2021.

My main question for everyone applying is two recruiters have told me the May 2022 board may end up cancelling. Has anyone heard about this? I’ve tried to search it but have not found anything. Just looking for some guidance. Thanks!

I actually asked my recruiter about this last week and he said he hadn’t heard anything about it, yet that is.

 

[exNavyOffRec]

Hey everyone! Looking at putting in my application in for the May 2022 board. I have studied for the ASTB. I’m a current flight instructor and graduated last May of 2021.

My main question for everyone applying is two recruiters have told me the May 2022 board may end up cancelling. Has anyone heard about this? I’ve tried to search it but have not found anything. Just looking for some guidance. Thanks!

Normally the May board would be essentially the first board picking FY 23 selects, however the last board put nearly everyone in FY 23 and the board prior had many moved to FY 23 after they received FY 22 spots, with the total number people moved + those selected last board for FY 23 nearly equaling the total number of spots for FY 22 this does lead to concerns for May being cancelled.

 

[Maze_soba]

If you go the the Nov board spread sheet there is the at board list in a different tab with everybody's scores from the board. You can cross check those with who was selected on the official release document to get some more data points if you haven't done that already. 300+ applicants total on the board. ?‍♂️

I'll have to check that out!!