Welcome to the Movie Recommender System! This AI-powered system recommends 5 similar types of movies based on user's choices using machine learning techniques.
- Content-based Recommendation: The system utilizes a content-based approach to recommend movies to users. It analyzes the features of movies and suggests similar ones based on user preferences.
- Machine Learning Model: The recommendation model is trained on the TMDB dataset, which provides comprehensive movie information. The model incorporates the Cosine Similarity algorithm for final recommendation and utilizes NLTK for feature extraction.
- Deployment and Visualization: The project is deployed on Streamlit, a user-friendly web framework for Python. The system showcases the output recommendations along with relevant images obtained from the TMDB API.
- User Input: Users provide their movie preferences or choices.
- Feature Extraction: The system uses NLTK (Natural Language Toolkit) to extract relevant features from the user's input.
- Cosine Similarity: The extracted features are compared with the movie dataset using the Cosine Similarity algorithm to find similar movies.
- Top Recommendations: The system generates a list of the top 5 movie recommendations based on the user's choices.
- Output Visualization: The recommended movies are displayed along with images fetched from the TMDB API for a visually appealing experience.
The model is trained on the TMDB dataset, which contains a vast collection of movie information. The dataset provides valuable features that are used for movie recommendations.
The Movie Recommender System is built using the following technologies:
- Python: Programming language used for model training and development.
- Machine Learning Libraries: NLTK and Cosine Similarity algorithm for feature extraction and recommendation.
- Streamlit: Web framework used for deploying the system and creating an interactive user interface.
- TMDB API: API used for fetching movie information and images.
You can see the Project demo below: