1
$\begingroup$

Are they using the words "feature", "attribute", and "decision variable" interchangeably in this paper about an optimization method for clustering (and if so, does that go against the general use of the terms)? I've been a bit confused especially about what they really mean when they say "decision variable" since I don't see how their use of it differs from feature, but I can't find any info on google suggesting that they would mean the same thing. I don't have any formal data science education either.

Some quotes:

  • "Mutation is a probabilistic operator that randomly modifies a decision variable of a candidate solution."
  • "Suppose [...] POPi(s) is the sth decision variable of POPi  (i.e.  C r t, t = 1,2,…, d  and  r = 1,2,…, q)."
  • "[...] max⁡(h i(SIV)),  min⁡(h i(SIV)) are the upper and lower bounds for each decision variable [...]"
  • "A SIV is a feature of the solution and can be imagined like a gene in GA."
Improve this question
$\endgroup$
5
  • $\begingroup$ You're right, it looked very cluttered as well. Thanks! $\endgroup$
    – A_Weierstrass
    Jul 19, 2019 at 2:59
  • $\begingroup$ Please don't take papers in this journal too seriously... This is an Open Access journal, where anybody can publish almost anything for a fee $\endgroup$
    – HEKTO
    Jul 19, 2019 at 14:20
  • $\begingroup$ @HEKTO I understand. Perhaps this is why I was reluctant to post the link in the first time - because my question is actually if there is a (conventional?) difference in general, but I just mentioned the article in case somebody wants an example. $\endgroup$
    – A_Weierstrass
    Jul 28, 2019 at 4:09
  • $\begingroup$ The question you ask doesn't appear to be the question you want answered. "Could there be a difference...in the same paper?" is a broad question that asks whether it possible there exists any paper where there is a difference. That is probably too broad to admit an answer that is likely to be useful to others, and I'm not sure it is really about computer science. "Could there be a difference in this specific paper?" is a different question. "Is there a difference in this specific paper?" is yet another question. I suggest being precise about exactly what you want answered. $\endgroup$
    – D.W. ♦
    Dec 6, 2021 at 5:27
  • $\begingroup$ That's a good point. Looking at it now I think I wanted to know if they have the same meaning in general, but was then still confused when trying to understand the paper (for example after 89f3a1c's answer). It would be better to ask about the specific paper and leave it open for people to point out if they think that the authors should have used other terms. Edited it to reflect that. $\endgroup$
    – A_Weierstrass
    Dec 25, 2021 at 7:42

1 Answer 1

Reset to default
1
$\begingroup$

Feature and attribute have both the same meaning.

Decision variable is the variable which is used to make a split in a decision tree in tree based algorithms, i.e. the variable on which the decision is made.

Improve this answer
$\endgroup$
1
  • 1
    $\begingroup$ Thanks for the reply, please see the article above though. It is not about decision trees. $\endgroup$
    – A_Weierstrass
    Jul 18, 2019 at 3:15

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.