This project implements a book recommendation system using machine learning techniques. It leverages user preferences, book ratings, and similarity scores to recommend books to users. The system is trained using various datasets and can generate recommendations based on the similarity between books or users' preferences.
- Python: The core programming language used in this project.
- Jupyter Notebook: For experimenting and building the recommendation model.
- Pandas: For data manipulation and preprocessing.
- Pickle: For serializing and storing models and data.
- Scikit-learn: For machine learning algorithms (if applicable).
- Flask/Django: For web app deployment (if applicable).
- app.py: The main Python file for the deployment of the book recommendation system (if you're using Flask/Django).
- book-recommender-system.ipynb: The Jupyter notebook where the recommendation system is developed and tested.
- books.pkl: Serialized file storing the book data used in the recommendation system.
- popular.pkl: Serialized file storing popular book data, used for recommending top-rated books.
- pt.pkl: A processed form of the data or an intermediate model for prediction.
- similarity_scores.pkl: Serialized file containing similarity scores used for generating book recommendations based on similarity.