This project aims to build a book recommendation system using the K-nearest neighbors (KNN) algorithm. The system takes in user input about their book preferences and recommends books similar to their interests based on the KNN algorithm. Additionally, the project also analyzes the dataset and visualizes key KPIs using barplots.
The dataset used for this project is the Goodreads books dataset, which contains information about over 10,000 books, including title, author, rating, and genre.
Python 3.6 or higher pandas numpy scikit-learn matplotlib
Clone this repository to your local machine. Navigate to the project directory in your terminal. Run pip install -r requirements.txt to install the required packages. Run python main.py to start the book recommendation system. Follow the prompts to input your book preferences and receive recommendations. KPI Visualizations This project includes barplot visualizations of the following key performance indicators (KPIs):
Number of books by genre Average rating by genre Number of books by author These visualizations can be found in the visualizations folder.
Implement other recommendation algorithms (e.g., collaborative filtering) Increase the size of the dataset for more accurate recommendations Improve the user interface for easier input and visualization of recommendations
Prateek Kumar Kumbar Please feel free to contribute to this project by submitting a pull request.