0

I have a dataset that has 3 columns. Customer, Shop, and # of times that a customer has shopped in a particular shop.

     Here's a subset of my data:
3   291 1
3   311 1
3   242 1
3   272 1
3   351 1
3   487 1
6   121 1
6   134 1
6   615 1
6   154 2
6   687 1
6   959 1
6   522 1
6   217 1
6   429 1
6   461 1
6   462 1
6   491 1
6   635 1
6   644 1
6   756 1
6   754 2

I need to come up with a model that depicts a probability that a customer will purchase at a particular shop. I have tried NMF and Naive Bayes but was unsuccessful. I am a beginner and I am having trouble coming up with a model.

potatopainting
  • 103
  • 1
  • 9
  • what means each column... is veri important know the nature of problem to select adecuade algorithm.. first you must decide if you problem is supervised, unsupervised or semi-supervised. – Egalicia Aug 18 '18 at 18:03
  • Looks like a cf problem. But you need understand how the customer have the relations with the shops and the #times – juanbits Aug 18 '18 at 18:07
  • from what i see the # of times relates the customer and the store to each other, am I right? – potatopainting Aug 18 '18 at 19:53

0 Answers0