MelodyMind offers personalized music recommendations, from a real-time Last.fm API-powered app to an advanced hybrid system combining content-based and collaborative filtering with LightFM.

Experience a comprehensive exploration of Spotify's musical landscape seamlessly transitioned from Tableau visualizations to SQL analysis. Dive into track inventory, streaming metrics, and sonic trends via interactive dashboards, while leveraging SQL queries for deeper insights into KPIs and cross-platform rankings.

Created multiple models to analyze a Spotify dataset and predict playlist genre. Dataset download from Kaggle (https://www.kaggle.com/datasets/joebeachcapital/30000-spotify-songs).

Content-based recommendation using clustering algorithms Status: #in-progress

A music recommendation system that uses NLP techniques and cosine similarity to analyze song descriptions/metadata and recommend similar music tracks based on user selection.

Interactive Power BI dashboard analyzing personal Spotify listening patterns across 13K tracks, 3,835 artists, and 7,383 albums. Features peak listening heatmaps, YoY trends, and quadrant analysis revealing music consumption insights.

🔎 M.EIC 2021/2022 - 1ˢᵗ year / 1ˢᵗ semester

Recommends songs from dataset of 232K songs from Spotify. Uses HDBSCAN and Siamese Network. An ML Project

Exploratory Spotify Data Analysis is a project where I analyzed Spotify’s music dataset to uncover trends in audio features and song popularity. Using Python and data visualization tools

Spotify recommendations using Python 🐍

Analyzed personal music data for the Maven Music Challenge, creating a 2024 "Spotify Wrapped" experience. Highlights include top songs, artists, along with insights into listening trends and peak months.

This repository contains implementations of track popularity prediction using both machine learning and deep learning approaches on the Spotify dataset. The ML notebook explores traditional machine learning algorithms, while the DL notebook applies deep learning techniques to predict song popularity.

The aim of this analysis is to understand the factors that influence the popularity of songs and use these insights to create predictive models that can accurately estimate a song's success.

Implementazione di un sistema di raccomandazione di playlist musicali basato su K-Means Clustering, e di algoritmi quali Random Forest, K-Nearest Neighbors, Decision Tree e Regressione Logistica per la predizione della popolaritá di una canzone.

It identifies songs and artists from lyric snippets using two distinct methods - simple NLP based approach and BM25(Best Match 25) approach.

Data Science Foundations II | Statistics Fundamentals for Data Science | Sampling for Data Science

Data analysis of Taylor Swift's Spotify discography using Python. Exploring correlations between track popularity, duration, and artist trends with Pandas and Seaborn

Implements a content-based recommendation system for Spotify using TF-IDF (Term Frequency-Inverse Document Frequency) and Cosine Similarity. The system analyzes song features to recommend similar tracks based on user preferences.

Extract spotify track details from spotify database using this python script