I'm working on a recommender system for a set of niche products. These are products that don't have a large number of customers. Does anyone have any tips on algorithms or approaches that work well for personalizing recommendations for small sets of customers?

  • $\begingroup$ why would you bother? ie if ther is no demand for the product the improvement you will get is not worth the effort you put in? $\endgroup$ – seanv507 Sep 19 '18 at 23:34
  • $\begingroup$ @seanv507 they're high dollar items. So we're trying to personalize recommendations for a small number of customers that we make a lot off of. $\endgroup$ – user3476463 Sep 20 '18 at 14:03
  • $\begingroup$ sorry to be unhrelpful, but high value, low data => human service? maybe you could quantify and give more details... one approach would be building a 'causal' model with a lot of expert input (ie people buy x because ,,,), rather than the usual collaborative filtering $\endgroup$ – seanv507 Sep 21 '18 at 12:10

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.