1

I am trying to apply weighted majority voting on an ensemble as a combiner method. I read different papers and articles, however, I am still a bit lost on:

  1. How the weighted majority voting works

  2. How to assign a weight for every ensemble base classifiers when using weighted majority voting.

desertnaut
  • 1,908
  • 2
  • 13
  • 23
s_am
  • 53
  • 5

1 Answers1

1

You can test each base classifier on a hold-out dataset and come up with a performance metric say accuracy for each model. You can then use each model's accuracy as a weight when combining predictions in the ensemble.

Here is a useful article.

Ethan
  • 1,625
  • 8
  • 23
  • 39
Jayaram Iyer
  • 785
  • 5
  • 8