CineMatch Recommender System is a movie recommendation application developed using advanced Natural Language Processing (NLP) techniques and Machine Learning algorithms.
The system preprocesses movie descriptions using techniques like stemming and lemmatization and transforms the text data into numerical features using the Bag of Words model. The recommendations are then generated using Recurrent Neural Networks (RNN). The front end is built with Streamlit, offering an interactive and user-friendly interface.
The datasets used for this project are : "tmbd_5000_movies" and "tmdb_5000_credits" which are available on KAGGLE
Features NLP and Machine Learning Techniques:
Implemented stemming and lemmatization to preprocess movie descriptions. Utilized the Bag of Words technique for feature extraction. Employed various RNN techniques to generate accurate movie recommendations. Interactive Front End:
Built using Streamlit, a Python framework for creating web applications.
Provides a real-time, user-friendly interface for receiving movie recommendations based on user input.
