# Feature ranking based on subtraction methods

- Institution: CERN
- Department: LPCC Workshops
- Speaker: Paul Glaysher
- Year: 2019
- Language: English
- Subjects: Computer science
- Source: [CERN](https://videos.cern.ch/record/3006260)
- Licence: [CERN](http://copyright.web.cern.ch)
- Who can watch: Tweens profiles and older (sources give no ratings; placed by Invisible Network from the source's own words)

The input variables of ML methods in physics analysis are often highly correlated and figuring out which ones are the most important ones for the classification turns out to be a non-trivial tasks. We compare the standard method of TMVA to rank variables with a several newly developed methods based on iterative removal for the use case of a search for top pair associated Higgs production (ttH) in the Higgs to b-pair decay channel..

0:00:00 Slide 1

0:00:17 Slide 2

0:01:26 Slide 3

0:03:06 Slide 4

0:04:51 Slide 5

0:06:11 Slide 6

0:07:06 Slide 7

0:07:33 Slide 8

0:07:41 Slide 9

0:07:58 Slide 10

0:10:19 Slide 11

0:10:48 Slide 12

0:11:29 Slide 13

0:11:53 Slide 14

0:12:24 Slide 15

0:12:54 Slide 16

0:13:34 Slide 17

0:14:33 Slide 18

0:15:10 Slide 19

0:16:36 Slide 20

0:16:50 Slide 21

## Lectures

1. [Feature ranking based on subtraction methods](https://invisiblenetwork.ai/learn/cern/3006260/b97797fb1656), 21 min (CERN's player)