Skip to content

oliviaxyl/A-Simple-Movie-Recommender-System-to-Classmates-

Repository files navigation

A-Simple-Movie-Recommender-System-to-Classmates-

movie

-- Project Status: [Completed]

Project Objective

The purpose of this coursework is to implement recommendation techniques and suggest relevant movies to classmates.

Methods Used

  • Item-based collaborative filter
  • User-based collaborative filter
  • Low-rank approximation
  • Neural collaborative filtering

Technologies

  • R
  • Jupyter, Python 3
  • Pandas, Numpy, matplotlib, sklearn, keras

Project Description

Data

  • User-based matrix U: 46 (Users) * 14 ('Gender' + 'Favorite Color' + 12 Genres 0/1)

  • Item-based matrix I: 20 (Movies) * 12 (Genres)

  • Rating matrix l: 20 (Movie ratings scaled in 1-5) * 46 (Users)

  • Users similarity matrix: 46 * 46

  • Items similarity matrix: 20 * 20

Recommendation Techniques

  • User-based collaborative filter

user

  • Item-based collaborative filter

item

  • Matrix completion (low-rank matrix approximation via nuclear norm minimization)

matrixcompletion

  • Neural matrix factorization

NeuMF

Results

  • NeuMF model test MAE: 0.7

maeplot

  • Top 5 movies recommended for the desired user:

neu

  • Rating from the desired user:

true

Reference

Package ‘softImpute’ https://cran.r-project.org/web/packages/softImpute/softImpute.pdf

SVD example https://www.d.umn.edu/~mhampton/m4326svd_example.pdf

Matrix Completion and Low-Rank SVD via Fast Alternating Least Squares https://arxiv.org/pdf/1410.2596.pdf

A Simple Algorithm for Nuclear Norm Regularized Problems https://www.m8j.net/data/List/Files-149/fastRegNuclearNormOptimization.pdf

Recommondation Systems https://developers.google.com/machine-learning/recommendation/collaborative/matrix

How to Implement a Recommendation System with Deep Learning and PyTorch https://medium.com/coinmonks/how-to-implement-a-recommendation-system-with-deep-learning-and-pytorch-2d40476590f9

Neural Collaborative Filtering (NCF) Explanation & Implementation in Pytorch https://www.youtube.com/watch?v=O4lk9Lw7lS0

Neural Collaborative Filtering (paper) https://arxiv.org/pdf/1708.05031.pdf

Matrix Factorization https://cims.nyu.edu/~cfgranda/pages/OBDA_fall17/notes/matrix_factorization.pdf

Neural Collaborative Filtering (Towards Data Science) https://towardsdatascience.com/neural-collaborative-filtering-96cef1009401

Neural Networks for Collaborative Filtering(keras example) https://nipunbatra.github.io/blog/ml/2017/12/29/neural-collaborative-filtering.html

Neural Collaborative Filtering with NeuMF http://caravanuden.com/spotify_recsys/neural_collaborative_filtering.html

Neural Networks for Collaborative Filtering https://nipunbatra.github.io/blog/ml/2017/12/29/neural-collaborative-filtering.html

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published