0
$\begingroup$

This is more of a theoretical/solving an argument sort of question.

Assuming I have a bunch of data point with 11 features I consider relevant about each point and 2 "labels": one is a boolean label ( 0 or 1), one is a continuous "label" (thought I'm not sure the word label really applies here).

What I want to do is basically: Find a way to predict both of these labels as accurately as possible. Find the features which influence these labels the most (even if by finding said features I'm unable to find a strong equation for actually predicting the labels).

Also, of note would be the fact that, although I care about both labels, predicting the second would automatically mean I predict the first and predicting the first is enough to "solve" the problem in most cases. With me until now? Ok, perfect.

Someone suggested to me that this would be a perfect scenario to apply clustering algorithms, but I'm not quite sure why. I was under the impression that clustering, generally speaking, is used to label unlabeled data (I have labeled data here) and for actually making predictions on unlabeled data a regression (be it with a SVM, a NN or w/e) or classification type algorithm is what can be used.

The only situation in which I could see clustering being used here is to turn the continuous label into a fixed number of labels.

Is there another situation in which a clustering algorithm can be applied to this sort of problem? Are there ways to use clustering algorithms to predict already existing labels or figure out if there is even a relation at all between a given label and a feature? Can clustering algorithms be used to filter out irrelevant features?

$\endgroup$
4
  • $\begingroup$ My suggestion would be to use some-kind of machine learning algorithm on the second label. Then you can deduce the first label from the results you got for the second label. Why do you want to use a clustering algorithm? $\endgroup$
    – dimpol
    Nov 7, 2016 at 11:09
  • $\begingroup$ I don't. As I said, I have this type of data and someone "suggested" using a clustering algorithm. I'm quite falbargasted by the fact that he did so since, to my knowledge, clustering algorithm are, by defintion, used for labeling data (which Is either not fully labeled or not labeled at all). $\endgroup$
    – George H
    Nov 7, 2016 at 11:16
  • $\begingroup$ Clustering algorithm can be used on labelled-data. It can be seen as a special case of categorization, where specifically you categorize data that are 'near' each other in some way. The reason you might choose such a special case is either because you have no labels and can't use more general methods, or because you know that the should be clustered is some way and you want to make sure the algorithm tries to find those clusters. $\endgroup$
    – dimpol
    Nov 7, 2016 at 11:49
  • $\begingroup$ Whoever suggested clustering here, probably just played buzzword bingo... $\endgroup$ Nov 7, 2016 at 20:49

1 Answer 1

2
$\begingroup$

Clustering algorithms will always perform much much worse compared to classification methods.

If you have labels, use classification or regression instead of clustering!

The reason is simple:

The clustering does not know which problem to solve, and there may well be more than one. You have no control over it solving anything related to your task.

For example, you might want to predict of a user will buy the product (classification) or the amount of money/time he spends on your site (regression). A clustering algorithm, since it does no know what you are interested in, may consider it more important to cluster your users by the weekday the, first visited your site... which may be a very good clustering, yet essentially useless for your business.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.