Overview
This project analyzes Spotify tracks to identify which features contribute most to a song's popularity. It includes feature engineering, data visualization, and regression model evaluation.
Dataset
Volum: 120,000 rows, 21 columns
The dataset contains 114,000+ songs with metadata and audio features extracted from Spotify’s Web API.
Methods
Exploratory Data Analysis (EDA)
Feature Engineering
Model training: Linear Regression, Random Forest, Gradient Boosting
Performance evaluation: R², MSE
Libraries Used
pandas, numpy, matplotlib, seaborn, sklearn