Melo Maniac is an AI-powered music discovery application prototype designed to recommend songs. Recognizing that popular platforms like Spotify and YouTube often reinforce existing listening patterns and limit musical exploration, I'm developing a concept for a system that surfaces hidden gems aligned with users' tastes but buried beneath popular streaming recommendations.
This project combines machine learning capabilities and comprehensive music datasets to create a more meaningful recommendation experience. The technical foundation involved extensive research with large-scale music databases. I've conducted early AI experimentation with Hugging Face models for recommendation and embedding generation, while also designing a user interface through Figma wireframing. The major challenge lies in translating complex AI processes into simple, engaging interactions.
This project is in development. It focuses on combining AI research, data engineering, and user experience design to address real-world problems in creative content discovery.
