3

I'm having difficulty searching for the original published paper proposing k-Means as an algorithm. I have been inspired to find it as reference for similar work, inspired by this TowardsDataScience article.

I have tried wiki's references and Google Scholar but with no luck.

desertnaut
  • 1,988
  • 2
  • 14
  • 23
StressedBoi3
  • 43
  • 5
  • 1
    Afaik there's no systematic method, but in general the idea is to follow the citations: find an article which uses the method you're looking for, see which paper they cite for the method: normally either they directly cite the original paper, or they cite another paper or book on which they rely (in which case follow up to this paper/book). But sometimes they don't cite anything and you're stuck. Also in general the original paper has lots of citations so it's quite easy to find, but that's not always true for papers published more than 30-40 years ago. – Erwan Apr 12 '21 at 22:43
  • Yes, I've discovered this to be true about older research papers. Ty – StressedBoi3 Apr 13 '21 at 09:47

1 Answers1

3

According to the Wikipedia article, it doesn't look like there is a definitive research article that introduced the k-means clustering algorithm.

Hugo Steinhaus had the original idea in 1956. The standard algorithm was proposed by Stuart Lloyd at Bell Labs in 1957, but apparently that wasn't published until 1982.

desertnaut
  • 1,988
  • 2
  • 14
  • 23
CoveredInChocolate
  • 171
  • 3