This experiment runs on three sample data sets from Azure. This aims on finding related restaurants based on the received customers' ratings
For this experiment, I mainly used the Restaurants ratings data set. The data set didn't require any wrangling or clean up and already followed the user-item-rating triplet structure that is needed for the matchbox recommendation module I am planning to use in this experiment I have followed the below steps in running my experiment, 1. I have split the restaurant ratings data set into data set and test set 2. I have used the matchbox recommendation module and have chosen the Related Item option from the list of options under this module 3. I have trained my model using the restaurant ratings data sets along with two more data sets; the Restaurant customers and restaurants data sets. I have set that my model uses 10 traits for both users (customers) and items (restaurants) 4. I have scored my matchbox trained model 5. I have applied some work on the scored data set bto make it more readable and user friendly by join it with the restaurants data set, in an effort to replace the IDs with readable names. I have split the data set into data set and test set.