How to Build a Spotify Recommendation Engine Using Kafka and Memgraph

In a company-wide hackathon, a team developed a Spotify song recommendation engine using Kafka, Memgraph, and a web application backend, utilizing an open dataset of Spotify playlists. The application leverages a graph data model to store and analyze data, using custom MAGE algorithms to recommend tracks and playlists based on user preferences and trending popularity. Users can interact with a Vue.js interface to create playlists, which dynamically updates recommendations as new songs are added. The backend is powered by a Python Flask application that handles various REST endpoints for playlist and track management. The project demonstrates the potential of Memgraph for building real-time applications and invites users to explore the system through GitHub and community channels.