You are viewing a plain text version of this content. The canonical link for it is here.

Posted to dev@bigtop.apache.org by "RJ Nowling (JIRA)" <ji...@apache.org> on 2014/11/19 05:32:34 UTC

[jira] [Created] (BIGTOP-1538) Add customer clustering example to BPS Spark

RJ Nowling created BIGTOP-1538:
----------------------------------

             Summary: Add customer clustering example to BPS Spark
                 Key: BIGTOP-1538
                 URL: https://issues.apache.org/jira/browse/BIGTOP-1538
             Project: Bigtop
          Issue Type: Improvement
          Components: blueprints
            Reporter: RJ Nowling


We should add an example for how to cluster customers based on purchasing habits.

Possible approaches for generating vectors:
1. Calculate probabilities of purchasing same item, brands, flavors, and quantities repeatedly and cluster vector of probabilities.  (Customer transactions need to be sorted by date / time first)

2. For each customer, create vector of normalized purchase counts for each product.  



--
This message was sent by Atlassian JIRA
(v6.3.4#6332)