Is there any data sets / methods available to find correlation between different 'bands' ?

Brands : Puma, Google, Microsoft, Nike, BMW etc

Is there any open data set available to find this correlation ? Also what are the different attributes/ methods that can be used to find correlation between them ?

eg : Nike is similar to Adidas with score say 0.9 (fitness brands) Nike is similar to Levis with score say 0.3 (apparels brands) Nike is similar to Google with score say 0.0 (different industry)

  • What do you mean by correlation between different bands?
    – Dawny33
    Jan 6 '16 at 11:49
  • Compare the brands' products. See how similar they are, collectively.
    – Emre
    Jan 7 '16 at 1:43
  • If the question is about finding data to use, then this might be the correct site ... if it's about methods to find correlation between the data, datascience.SE (where you originally posted it to) would've been the better place for it.
    – Joe
    Jan 10 '16 at 14:28

You should clarify your question, maybe giving more details about the application. There are many different ways a brand can be similar (or correlated) to another one, for example:

  1. Correlation of stock trends. In this case, dataset can be found in yahoo finance, for example.
  2. "Product Space" Analysis
  3. By clustering features of each company
  • thanks, do you know any source from where I can get some sample data for clustering features ? Jan 7 '16 at 3:46
  • For US companies, for example, you can try opendata500.com/us/list. Even though, the data available may not be enough to your study.
    – Bernardo Aflalo
    Jan 7 '16 at 10:46

You should look for semantic similarity. The normalized Google distance should be a good place to start, and gives the kind of [0-1] rating you are looking for.

The Normalized Google Distance is a semantic similarity measure derived from the number of hits returned by the Google search engine for a given set of keywords.1 Keywords with the same or similar meanings in a natural language sense tend to be "close" in units of Normalized Google Distance, while words with dissimilar meanings tend to be farther apart.


Your Answer

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

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