/Item-Recommender-System

This project implement a simple user - based collaborative filtering recommender system for predicting the ratings of an item using the data given. This prediction is done using k nearest neighbors and Pearson correlation. Finally using the similarity of the k nearest neighbors, ratings of the new item for the given user can be predicted

Primary LanguagePython

#Item Recommender system

##Running this code

The program takes 4 arguments

  • Ratings input file
  • User id (user name)
  • Movie name to calculate prediction for
  • K for k neighbors

##Execution

python collabFilter.py ratings-dataset.tsv Kluver "The Fugitive" 10

  • dataset.tsv: input file
  • Kluver: User id
  • Movie: The Fugitive
  • K: 10

##Output:

The program will output:

  • K nearest neighbors with their user ids and similarity values separated by space as per the output file
  • Rating prediction for item