How to get feature rank while using advise(NEURAL)

Gamestudio Links

Zorro Links

Trading Journey
by 7th_zorro. 04/27/24 04:42

M1 Oversampling
by jcl. 04/26/24 11:12

Eigenwerbung
by jcl. 04/26/24 11:08

AUM Magazine

Latest Screens

4 registered members (Akow, Quad, 7th_zorro, VoroneTZ), 800 guests, and 5 spiders.

Key: Admin, Global Mod, Mod

Newest Members

Print Thread

Rate Thread

How to get feature rank while using advise(NEURAL) #465871 05/16/17 03:22 05/16/17 03:22
Joined: Nov 2016 Posts: 55 Taipei ytc OP Junior Member
ytc OP Junior Member Joined: Nov 2016 Posts: 55 Taipei	I'm practicing feature selection. I got stuck in getting feature rank and profit factor at the same time. How can I get feature rank/importance while using advise(NEURAL) with simple linear regression like lm() in each WFO cycle? Thanks.

Re: How to get feature rank while using advise(NEURAL) [Re: ytc] #465880 05/16/17 11:08 05/16/17 11:08
Joined: Jul 2000 Posts: 27,986 Frankfurt jcl Chief Engineer
jcl Chief Engineer Joined: Jul 2000 Posts: 27,986 Frankfurt	Feature rank is a separate process that you do before training the network. There are several R packages for generating feature rank, f.i. Boruta.

Moderated by Petra