A movie recommendation system built using cosine similarity algorithm.
1.) Data Preprocessing: At first, the dataset is cleaned. After data cleaning, I combined overview, genres, keywords into a single column tags.
2.) Vectorization: I have used Bag of Words to tokenize the input sequences. I have used CountVectorizer for this.
3.) Cosine Similarity: I calculated cosine similarity among each vectors and stored them as a matrix similarity.
