Datasets: https://www.kaggle.com/datasets/tmdb/tmdb-movie-metadata
Content-based recommendation systems are a popular and widely used approach to provide personalized recommendations to users. These systems are based on the idea that a user’s preferences can be predicted based on their previous interactions with items, such as their viewing and purchasing history. The goal of a content-based recommendation system is to recommend items to a user that are similar to items that they have previously interacted with.
We will use a simple bag of words algorithm first and then we will use word2vec vectorization algorithm with a bit of stemming to find most optimal recommendations and deploy it on streamlit. the TMDB dataset is used so as to involve both the plot of the movie and the cast and director into it. This improves the recommendations by a good deal.
