0
$\begingroup$

I have multiple groups of customer, say for segment 1 as shown in the pictures, I have a list of products that I can choose the cross-sell to that group. Consider the product has multiple features, e.g., prices, types, how do I come up with a model that recommend top 3 products for the segment of customers?

The difficuties lie in: For segment of customers, we have range of values (e.g., for ALL_FEES we have \$13-\$4835), how to model that?

i

$\endgroup$
0
$\begingroup$

This is an interesting problem statement. If we have products purchased by all the users, We can try the following

  1. Perform Collaborative filtering for each metric e.g. ALL_FEES, ASSETS
  2. While performing Collaborative Filtering, we use userGroups instead of users
  3. For arriving at the top product recommendations for each user group, we choose products that have been recommended in most of the collaborative filtering metric model outputs
$\endgroup$

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.