Turn your Last.fm scrobbles into a complete, private dashboard.

A Chrome extension for tracking and analyzing streaming data on Spotify. Easily monitor playlist, album, and track streams, export data to Excel.

Interactive Streamlit dashboard that transforms a prepared listening-history dataset into rich insights: genres, mood/energy trends, discovery habits, device mix, streaks, artist comebacks, and ML-powered 7-day forecasts with confidence bands for platform share, trained offline and visualized directly in the app.

🎵 Plateforme full-stack d'analytics musicales avec recommandations personnalisées. MongoDB + NestJS + Next.js. Intégration Spotify, aggregation pipelines avancées, visualisations interactives.

A full-stack web application that transforms music discovery through interactive visualizations, personalized recommendations, and deep artist analytics. Built with the Spotify API, MusicBucket helps users explore new music, track their listening journey, and understand their musical preferences with rich data insights.

Spotify Stats is a privacy-focused web app that lets users explore their Spotify listening habits, including top artists, tracks, and genres. Built with Next.js, and Tailwind CSS, it offers secure authentication via NextAuth.js and integrates Plausible analytics for privacy-conscious tracking.

A Next.js application that lets you explore your Spotify listening history, create playlists based on specific time periods, and visualize your music journey.

🎧 A full-stack music search and analytics platform built with React, Node.js, PostgreSQL, and AWS RDS. Features advanced filtering, interactive visualizations, and RESTful APIs for exploring songs and albums.

Unsupervised ML project that clusters Amazon Music tracks by audio features (tempo, energy, danceability) using K-Means & DBSCAN. Includes EDA, PCA visualization, and an interactive Streamlit app for real-time cluster prediction. Perfect for playlist generation & music recommendations!

AI-powered vinyl cataloging and music discovery platform leveraging BigQuery’s generative AI. Processes mixed-format data to deliver personalized recommendations, collection analytics, and intelligent search. Created for the Kaggle BigQuery AI Challenge to showcase real-world, scalable AI solutions for music lovers.

An interactive Power BI project analyzing multi-year Spotify streaming history to uncover user listening patterns, peak activity times, and music preferences. The dashboard includes YOY growth analysis, heatmaps, top artist/album/track rankings, and quadrant segmentation of songs based on frequency and duration.

SQL analysis on the Chinook (SQLite) dataset: revenue trends, top customers, genres, RFM, cohorts.

Legit Spotify playlist automation

A full end-to-end machine learning pipeline that predicts Spotify track popularity using audio features and genre encoding. Includes preprocessing, model training, evaluation, and an interactive Streamlit app for real-time predictions and EDA.

End-to-end data analysis of 8,582 Spotify tracks to uncover what drives track popularity, focusing on artist popularity and followers, album type, track duration, genre, and release timing, and turning these insights into practical recommendations for artists, labels, playlist curators, and streaming platforms

This project analyses Spotify track data using linear regression models to explore relationships between audio features and track popularity. It includes Jupyter Notebooks demonstrating simple and multiple linear regression techniques

Shazam artist discovery scraper

Built SQL queries and aggregations to uncover trends in listening habits, popular genres, and user engagement metrics using Spotify dataset.

Analysis on music release through Youtube comments on relevant videos