📚 Book Recommendation System

🛠️ Tech Stack & Tools

Overview

This project builds a book recommendation system using data collected from multiple sources. The goal is to demonstrate an end-to-end data analytics workflow, including web scraping, API integration, data cleaning, exploratory analysis, and deployment.

The final system allows users to explore books and receive recommendations through an interactive web application.

Data Sources

Dataset	Source	Purpose
openlibrary	https://openlibrary.org/subjects/awards	Core data for books and awards given

Workflow

• Data collection (Scraping + API)

• Data cleaning & deduplication

• Exploratory analysis

• Content-based recommendation logic

• Deployment with Streamlit

Deployment

Streamlit

The final model was deployed using Streamlit to provide an interactive interface where users can:

• Browse books

• View cover images

• Filter by genre or award

• Receive recommendations

🔗 Streamlit App

here

Photo credit (https://www.pexels.com/de-de/foto/gestapelte-bucher-1333742/)

Presentation

A project presentation summarising the methodology, insights, and deployment is available below:

🎥 Project Presentation

here

Future Improvements

• Add user-rating or popularity data

• Implement similarity using text descriptions (NLP)

• Improve genre standardisation

• Expand dataset beyond 1000 books

• Deploy using a cloud hosting platform

---

👥 Team

Alan, Antonio, Ghazal, Charles