2

I'm trying to do a project about email marketing. I'm working on a tourism company and I want to make a best destination suggestion for the clients. But I need to see the relations between destinations.

Example: How many people visited Dublin and then visited London?

My question: How can I best analyse this relation between the cities, given data about traveler itineraries?

I want to send email offers to clients who went to London and didn't go to Dublin (assuming a strong relation between London and Dublin).

MrMeritology
  • 1,840
  • 13
  • 14
Uygar Yologlu
  • 23
  • 2
  • Have you read about item-based collaborative filtering or matrix factorization for recommender systems? Your problem is very much like Amazon's "customers who bought this also bought that." – aaryno Jun 25 '15 at 16:34

1 Answers1

0

You can try Graph databases (Neo4j/Orient DB etc). Store location and connection between the location as nodes and edges. Then do analysis over graph data. Based on your need, you can use additional attributes (like count) and assign weights for edges etc. Neo4j supports collaborative filtering also.

Sreejithc321
  • 1,920
  • 3
  • 18
  • 33