NETFLIX MOVIE RECOMMENDATION SYSTEM USING MACHINE LEARNING
The system starts by loading movie data from a CSV file using the pandas library. It then explores the dataset, examining characteristics like summary statistics and missing values to understand its structure. Relevant features such as movie ID, title, overview, and genre are selected from the dataset. These features are combined into a single "tags" column to capture key movie attributes. Next, the system performs movie recommendation using text vectorization, converting text data into numerical vectors using CountVectorizer. It calculates cosine similarity between movie vectors to measure their similarity. A recommendation function (recommand()) is defined to suggest similar movies based on user input. Finally, testing and user interaction are conducted, where a sample of movie titles is provided for user reference. Users input a movie title they'd like to watch, and the system suggests similar movies based on their input.