The goal is to recommend Netflix movies based on their genres. The system allows users to input a movie title and receive recommendations of similar movies. The dataset containing movie titles, descriptions, content types, and genres is loaded and preprocessed. Text data (genres) is transformed into numerical form using TF-IDF vectors. Cosine similarity is calculated between TF-IDF vectors of different movies to determine their similarity. A function is created to take user input (movie title) and return recommendations based on similarity scores. Streamlit is employed to create a user-friendly interface, allowing users to input movie titles and view recommendations seamlessly.
Built With
- python
- streamlit
Log in or sign up for Devpost to join the conversation.