Key Findings:

1. Duration of Songs has increased since 1920s
2. Dance, Pop, Rap, Hip Hop and Raggaeton are most
   popular genres
3. With Loudness Popularity of Songs has increased
4. Loud songs are generally more Energetic

Author

• @Mridul-Gulati

Problem Statement:

This project analyses what kinds of music gain the most amount of listeners. It helps us get a detailed view of why some songs performed well while others didn't.

Data Source

• Spotify Tracks DB
• Spotify Datasets

Methods

• Defined the Problem Statement
• Data Cleaning using Pandas
• Feature Engineering - Correlation HeatMap
• Comparing Loudness and Energy
• Analysis of Most Popular genres

🛠 Tech Stack

• Python 3.10
• Pandas
• Matplotlib
• Seaborn

Quick Glance at Findings

Correlation between Features

Popular Genres

Comparing Loudness & Energy

Changing Duration of Songs with Time(Years)

Lessons learnt:

• How to Identify problem statements?
• How to use Data insights to solve the problems?
• How to perform Feature Engineering?
• How to use Seaborn for data visualization?

What to do next?

• Use the above insights to create a song recommendation system by grouping related songs one after the other.
• Predicting how a song would do according to its features like duration, loudness, genre etc.

🔗 Links