You are on page 1of 6

Movie Recommender Systems

By:
BATCH-1(Group-1)
Karam Shraddha
RAI MAYANK
BINNY JESHAN
Intro
• The project aims to build a simple movie
recommender system. The system makes an
extensive use of user data to come up with
reasonable track predictions about the user
preferences. The scope consists of determining
similar users according to the similarities between
their evaluations of certain track attributes. The
Recommender System will be a Web Service and
the end users will be directly exposed to the
suggestions made for them.
Approach
Prediction
New User input Matrix

input

LDA

output

User_Topic Vector

Calculate the mean of ratings of all the Input for


users for a particular movie in that cluster clustering
and recommend the highly rated movie to
the user
predict Assign K-Means cluster
Code snippet
Extracting a vector for single user:
lda =LatentDirichletAllocation(n_components=6)
user_topic = lda.fit_transform(ratingMatrix)
To be done
• Clustering
• Prediction

Overall 40% of the POC is completed.

You might also like