Re: Prediction in clustering

Although I don't have a reference for this, my intuition tells me that
if your data is amenable to supervised classification, then those
methods will be superior to clustering forced into predictive mode.

While Art cannot be faulted for pointing to software that allows you to
do prediction using cluster output, the mere existence of such software
does not say anything about whether they should be used or not. How
does those software tackle the many challenges I have outlined?

Jay wrote:
> Data Matter wrote:
>
> ....
> > Clustering first and foremost is for exploration.
> ....
>
> I absolutely agree with you. This is the very reason why I posted this
> topic. The primary purpose of many clustering methods is analyzing data
> exploratorily, rather than predicting cluster memberships as far as I
> know.
>
> I wanted to compare two approaches (one is based on classification
> techniques and the other based on clustering techniques) for a specific
> application. For on-line application of the two approaches, the
> approach based on classification is very straightforward but the one
> based on clustering is not. (I even felt a little bit awkward in saying
> "prediction in clustering").
>
> Thank you for sharing your thought on this.
>
> Jay

.

Relevant Pages

  • Re: finding the centre of a cluster
    ... for classification problems involves ... predictor variables are continuous, ... Clustering is an unstructured problem in which you DON'T KNOW even ... I have more experience with neural networks and decision trees than you do. ...
    (sci.stat.math)
  • Re: HELP!!!
    ... can be improved, significantly, if supervised clustering ... *If*, that is, the class labels are correct. ... The "Gold Standard" is classification by a trained experienced human ... classification methods have an accuracy significantly exceeding the ...
    (comp.soft-sys.matlab)
  • Re: assumption of Classification
    ... Most clustering algorithms (k-means, ... > A classification tree that tries to break at every value ... normality is not the only assumption to be checked. ...
    (sci.stat.edu)
  • Re: HELP!!!
    ... I need to perform some classification on the first raw of ... and perform the classification. ... clustering a mixture of multiple class data ... corresponding MATLAB code is readily available. ...
    (comp.soft-sys.matlab)
  • Re: assumption of Classification
    ... Classification trees do not. ... Most clustering algorithms (k-means, ... single link, average link, etc.) do not. ... normality is not the only assumption to be checked. ...
    (sci.stat.edu)
Loading