Hi Willi, Thanks for taking your time to reply!
That use case is indeed interesting but as they don't go into specifics it doesn't help me that much. >From what I have understood so far is that I should do a content-based filtering approach where each listing attribute is a vertex. I can then weight users relationship with these attributes and get some sort of listing score/distance. So if London is an important location to the user it will get a higher score. But I guess I would have to create relationships with all neighbouring locations as well with a lower weight for these to also be "recommended"? I'm not sure how I would do this approach when it comes to prices? Maybe create a price vertex where I would create "price interval" docs that have weighted relationships with the user depending on how close the price is to what the user wants? I haven't found that many examples online so any advice is much appreciated! Most examples always do a simple collaborative based approach using social interactions. Thanks! Michael -- You received this message because you are subscribed to the Google Groups "ArangoDB" group. To unsubscribe from this group and stop receiving emails from it, send an email to arangodb+unsubscr...@googlegroups.com. For more options, visit https://groups.google.com/d/optout.
