Movie Recommendation System is a Python Application with Collaborative Filtering and Vector Search Using MongoDB database, HuggingFace embeded Models , and Python Streamlit Library
Movie Recommendation System with Collaborative Filtering and Vector Search:
This project presents a movie recommendation system that combines both collaborative filtering and vector search techniques to recommend movies to users.
The core dataset includes 11,506 American movies released between 1970 and 2023, along with ratings from 11,675 users.
To address the cold-start problem, the system employs vector embeddings generated using the Sentence Transformer model. These embeddings capture semantic information beyond explicit ratings, allowing similarity comparisons even for unseen movies or users.
Additionally, the project explores hybrid filtering (under development), combining collaborative filtering with content-based filtering to potentially improve recommendation accuracy.
The vector search component uses Chroma DB, an open-source vector database, to store and retrieve movie and user embeddings1.
Movie Recommendation System using KNN and Text Vectorization:
This movie recommender system recommends five movies based on a given movie input.
It utilizes a K-Nearest Neighbors (KNN) model that operates on concept text vectorization.
The model leverages Hugging Face embeddings to create vector representations for movies, enabling efficient similarity comparisons and personalized recommendations2.
Feel free to explore either of these approaches based on your project requirements! 😊🎥
-
Notifications
You must be signed in to change notification settings - Fork 0
Movie Recommendation System is a Python Application with Collaborative Filtering and Vector Search Using MongoDB database, HuggingFace embeded Models , and Python Streamlit Library
vkix-7/Movie-Recommender-application
This commit does not belong to any branch on this repository, and may belong to a fork outside of the repository.
Folders and files
Name | Name | Last commit message | Last commit date | |
---|---|---|---|---|
Repository files navigation
About
Movie Recommendation System is a Python Application with Collaborative Filtering and Vector Search Using MongoDB database, HuggingFace embeded Models , and Python Streamlit Library
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published