0
$\begingroup$

I am exploring approaches to build a model that shows personalized search results (with or without query) for a fashion eCommerce platform. The data that I have are:

  1. Client's purchase history i.e the list of all the products with the client has bought with brand name and the dress category that the product belongs to (shoe or top etc.)
  2. Client's own brand preferences or dislikes that they have explicitly mentioned through a survey.

So I want to populate client's search results with the items that the client is most likely to purchase based on the query that he has entered. The products are part of a larger product inventory.

Is this a content based filtering problem? Currently I am trying to create each client's vector profile (50 clients) based on his liking towards a brand or not? Is this the current way.

$\endgroup$
  • $\begingroup$ Can you provide some example data? This would help answer the question. $\endgroup$ – bstrain Jul 1 at 17:00
0
$\begingroup$

You can use latent dirichlet allocation LDA recommender system, similar like described here: Building a tag-based recommendation engine given a set of user tags?

| improve this answer | |
$\endgroup$

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.