-1

I would like to ask, I have 10 columns with sound parameters and after 2 columns with which two instrument was recorded in this moment.

After I have data with 10 columns of sound parameters and I need to predict which single instrument was used.

I know about data pre processing and so on, but I would like to double check if I'm choosing the right classified. For the example I provided, would be appropriate to use, Naïve Bayes or Linear Regression or SVN?? I just confused which will be more appropriate for this particular example.

Has QUIT--Anony-Mousse
  • 76,138
  • 12
  • 138
  • 194
Denis
  • 79
  • 2
  • 13
  • 1
    why don't you try all of them and choose the one with the better results? – xro7 Nov 14 '16 at 08:30
  • @xro7 "Your submission will be evaluated using the classification error." - any thinking about most appropriate? – Denis Nov 14 '16 at 09:47
  • 1
    i don't know which is the best for your case but you could have already trained all three classifiers and choose the one with the smallest classification error :) – xro7 Nov 14 '16 at 10:03

1 Answers1

1

It's hard to predict which one will work best on your data.

Every data set is different. Sometimes A is better, sometimes B.

Therefore, try all of them, and use cross-validation to check which worked best.

Has QUIT--Anony-Mousse
  • 76,138
  • 12
  • 138
  • 194