1
$\begingroup$

I was going through algorithms for collaborative filtering-based prediction. Most of the places, I read about using matrix factorization based on ratings of the likeness of the user. But for my use case, I have to predict on the bases of classified data. For example, I have a list of user who orders from place1,place2, etc and they mostly get their items delivered to address1,address2 etc. Initially, I thought to give binary ratings to the places, but I am having multiple criteria i.e addresses and places. How can I use collaborative filtering in this case?

User Place Delivery Address
One X A
One X A
One Y C
Two Y C
Two Z B
Three Y ??
$\endgroup$
1
  • $\begingroup$ What are you trying to predict? $\endgroup$ Apr 14, 2021 at 10:38

1 Answer 1

0
$\begingroup$

Actually, your objective here is not clear. Following your example, I belive you want to obtain likeness/relationship between users and places.

So basically what you would want to do is to create a domain of users and places. Now for different addresses (eg. A and C), you can treat the same user (eg. One) as different users i.e. "One-A" and "One-C". You can now assign a binary value for each "user-address" v/s "place". Then you can use any collaborative filtering method to get the affinity of the users corresponding to a particular address, for a particular ordering place.

$\endgroup$

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.