I am trying to determine the apt algorithm for a ranking problem that I am working on. I have social media metrics - engagement, sentiment, audience size etc for several brands and am looking for a ranking / classification algorithm to rank them.

I am not sure if I have a dependent variable or label class for classical classification algorithms.

The data is aggregated by brands and algorithms needs to rank the brands based on the metrics.

Any ideas would be much appreciated.

  • $\begingroup$ Who is going to be presented and evaluate the ranked list, and what is the feedback going to look like? You have described auxiliary signals but not the main one that is going to drive the ranking function, as I understand it. $\endgroup$ – Emre Sep 13 '17 at 20:41
  • $\begingroup$ Brands. It's is essentially a rank/score of brands' relative performance of social media activity. @Emre $\endgroup$ – kms Sep 13 '17 at 20:45
  • $\begingroup$ The ranking function is driven by the metrics mentioned in the question - engagement, sentiment, audience size etc. The score/rank needs to be an indication of the relative performance of the brands. Hope this helps clarify. $\endgroup$ – kms Sep 13 '17 at 20:50
  • $\begingroup$ I don't see room for machine learning without some feedback on the list, so could you give us an example? Do you want to develop some sort of "Klout score"? $\endgroup$ – Emre Sep 13 '17 at 20:53
  • $\begingroup$ Alexa ranking algorithm is a good example. alexa.com/siteinfo. Their algorithm ranks domain based on a few site metrics. $\endgroup$ – kms Sep 13 '17 at 20:57

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.