LU
LunaticPrakash/Movie-Recommender
This project suggests you the list of movies based on the movie title that you have entered. It uses Count Vectorizer (Text-Feature Extraction tool) to find the relation between similar movies.
🎬 Movie Recommender
A full-stack content-based movie recommendation system that suggests similar movies using NLP techniques like TF-IDF and CountVectorizer. Users can search by title or filter by genre to receive intelligent recommendations based on metadata similarity.
Live Site:
🔗 https://movie-recommender-frontend-i255.onrender.com/
Technologies Used:
- Backend: Python, Flask, Scikit-learn, Joblib
- Frontend: ReactJS, Vite, Axios
- Deployment: Render (both frontend & backend)
Features:
- Smart search: Get similar movie recommendations based on title or genre.
- NLP-based logic: Supports both TF-IDF and CountVectorizer techniques for vector similarity.
- Fast API: Optimized model loading for sub-second response time.
- Deployed frontend with real-time search, filter by genre, and responsive design.
- Persistent model storage with Joblib to avoid recomputation and reduce memory usage.
Screenshots:
Dev:
Prakash Gupta