https://github.com/sanjaykumhar/movie-recommendation-system

A comprehensive movie recommendation system that employs three fundamental recommendation techniques i.e. Demographic filtering, Content-Based filtering and Collaborative filtering.
https://github.com/sanjaykumhar/movie-recommendation-system

cosine-similarity matplotlib-pyplot movie-recomendation-system python recommender-system scikitlearn-machine-learning svd-matrix-factorisation tf-idf

Last synced: 2 months ago
JSON representation

A comprehensive movie recommendation system that employs three fundamental recommendation techniques i.e. Demographic filtering, Content-Based filtering and Collaborative filtering.

• Host: GitHub
• URL: https://github.com/sanjaykumhar/movie-recommendation-system
• Owner: SanjayKumhar
• Created: 2024-12-12T08:44:06.000Z (11 months ago)
• Default Branch: main
• Last Pushed: 2024-12-12T09:04:50.000Z (11 months ago)
• Last Synced: 2025-04-04T06:41:29.505Z (8 months ago)
• Topics: cosine-similarity, matplotlib-pyplot, movie-recomendation-system, python, recommender-system, scikitlearn-machine-learning, svd-matrix-factorisation, tf-idf
• Language: Jupyter Notebook
• Homepage:
• Size: 9.31 MB
• Stars: 0
• Watchers: 1
• Forks: 0
• Open Issues: 0
• Metadata Files:
  • Readme: Readme.md

Awesome Lists containing this project

README

          
# **Movie Recommendation System**

This project demonstrates a comprehensive movie recommendation system that employs three fundamental recommendation techniques:

* Demographic Filtering: Recommends movies based on popularity and ratings, implementing the Weighted Rating formula.

* Content-Based Filtering: Suggests movies similar to those a user has liked, using TF-IDF Vectorizer and Cosine Similarity from Scikit-learn.

* Collaborative Filtering: Predicts user preferences using Singular Value Decomposition (SVD), a matrix factorization technique.

The system is designed to highlight the core principles and applications of recommendation systems in a real-world scenario.

## ***Features:***

* Demographic Filtering: Recommends highly rated and popular movies.

* Content-Based Filtering: Provides recommendations based on movie features (e.g., genres, keywords).

* Collaborative Filtering: Leverages user-movie interaction data to predict ratings for unseen movies.

* Detailed visualization of results for better understanding.

## ***Technologies Used:***

* Programming Language: Python

* Libraries:

    * pandas, numpy for data manipulation

    * scikit-learn for TF-IDF Vectorization and Cosine Similarity

    * surprise library for Collaborative Filtering (SVD implementation)

    * matplotlib for data visualization

* Dataset: https://www.kaggle.com/datasets/tmdb/tmdb-movie-metadata