The Hybrid Movie Recommender is a system that recommends movies using a combination of collaborative and content-based filtering techniques. The system is designed to address the cold start problem(new users) by using a popularity based approach. The dataset used for the system is obtained from Kaggle.
Collaborative filtering technique for recommending movies based on user preferences Content-based filtering technique for recommending movies based on the characteristics of the movies Popularity based approach to handle the cold start problem Personalized recommendations based on user history Ability to provide new user recommendations based on popular movies
- Python 3.7 or above
- Jupyter Notebook
- Pandas library
- matplotlib
- Surprise
- Scikit-learn library
- seaborn
- Numpy library
The dataset used in the system is obtained from Kaggle and contains movie ratings and movie metadata. The dataset is preprocessed and cleaned before being used in the system.
- link to the Dataset https://www.kaggle.com/datasets/rounakbanik/the-movies-dataset
Download or clone the repository to your local machine Open the Jupyter Notebook file in the repository Run the cells in the notebook to load the dataset and train the model Once the model is trained, you can use the system to recommend movies based on your preferences