Skip to content

Spotify Song & Genre Analysis, Popularity Prediction and Building a Simple Recommendation System

Notifications You must be signed in to change notification settings

gulbudakk/SpotifyDataScience

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

7 Commits
 
 
 
 
 
 

Repository files navigation

Spotify Song & Genre Analysis, Popularity Prediction and Building a Simple Recommendation System

Group Members:

  • Uğur Sezer Aşıkoğlu
  • Melisa Yılmaz
  • Kalender Gülbudak

Exploratory Data Analysis:

  • Visualizations descriptive statistics of the dataset; visual explanations of features & sharing distributions,
  • Example visualizations of aggregated forms based on features (One example can be grouping the dataset based on genres and comparing distributions or centrality metrics of features for different genres),
  • Analysis of the most popular artists and songs.
  • Analyzing how songs of different genres change with time (Temporal analysis of features)

Statistical Analysis & Hypothesis Testing:

  • Statistical tests to check how (or if) features contribute to popularity of songs
  • Statistical tests to check if significant differences exist between different eras (like comparing features of 80s and 90s hip-hop)

Machine Learning:

  • Prediction of song popularity with various machine learning models
  • Efforts on hyper-parameter tuning to increase the performance of models
  • Creating a simple song recommendation system using similarity metrics and Nearest Neighbors methods

About

Spotify Song & Genre Analysis, Popularity Prediction and Building a Simple Recommendation System

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published