This analysis of Spotify user data utilizes KModes clustering to reveal three distinct segments: free mainstream music listeners, playlist-oriented users, and premium-leaning podcast enthusiasts. The clustering results highlight differences in demographics, device usage, subscription preferences, and content choices, providing actionable insights for targeted marketing and product strategies. Association rule mining further uncovered cross-feature patterns. The project GitHub repository can be found here: Spotify User Segmentation Analysis Notebook
Clustering
KMODES
Association Analysis
August 2025
This project analyzes Spotify user data with the goal of uncovering patterns in user demographics, listening behaviors, and preferences. By applying clustering and association analysis, the project seeks to answer the following questions:
Identifying meaningful user segments helps businesses better understand their customer base and differentiate between distinct types of users. For Spotify, this knowledge could highlight what sets engaged listeners apart from stalled ones, or what drives satisfaction in certain listener groups. Comparing segments can guide product and marketing teams on how to increase engagement levels for lower-activity users, and reallocate resources away from less strategic segments.
A user behavior survey was developed consisting of twenty multiple choice questions regarding behavior patterns and preferences of Spotify users. The dataset was sourced from Kaggle and contains 520 records and 20 variables. The variables include: