Read-Radar is a Python-based book recommendation system developed as an academic project. The system utilizes exploratory data analysis, data visualization, and machine learning algorithms to provide personalized book recommendations. This repository contains the source code, Jupyter Notebook documentation, and additional resources for better understanding the project.
Exploratory Data Analysis (EDA): The project includes comprehensive exploratory data analysis to gain insights into the datasets used for building the recommendation system.
Data Visualization: Various visualization techniques have been employed to illustrate patterns, trends, and correlations within the datasets. Visualizations help in better understanding the underlying data and algorithms.
Logistic Regression: To determine if a book is more likely to have higher rating or lower rating.
TF-IDF Matrix (Text Analysis): Employed for extracting meaningful features from textual data especially to make the search functionality more effective.
Collaborative Filtering: Implemented to enhance the accuracy of book recommendations by considering user preferences and behaviors.
app.py: Contains the Streamlit frontend for the recommendation system.
ReadRadarProject.ipynb: Jupyter Notebook with step-by-step documentation, providing insights into the development process.
datasets: These need to be accessed via this link https://mengtingwan.github.io/data/goodreads.html#datasets
Read-Radar.pptx: PowerPoint presentation providing a user-friendly overview of the project journey.
Rida Khan (katastrophe-codes)
This project is licensed under the MIT License.
Feel free to contribute, report issues, or provide feedback. Happy reading with Read-Radar! 📚🚀