Analysis of Trendy Music and Playlists
on Spotify

In the 3rd quarter earning call, Spotify’s total Monthly Active Users grew 19% to 381 million in the quarter, up from 365 million last quarter. According to the latest earning call, Spotify experienced double-digit growth in all regions. We’re going to dive into the secret recipe of Spotify’s most popular songs in this study.

Project Information:
Teamed up with three Business Analytics students at UC, my main responsibilities in this project were to finish data preparation, direct the overall structure, as well as be actively engaged in every step, enhancing my analytical skills from the whole process.
Duration: 3 months
32833 Observations, 23 independent variables
Data source: https://github.com/rfordatascience/tidytuesday/blob/master/data/2020/2020-01-21/readme.md

Goals:

Discover the General Music Trends for Musicians
Assist Spotify Staff on Music Selection for Playlist
Direction for Artists’ Music Creation

Track Analysis:

How are danceability, speechiness, energy, acousticness, liveness, valence’s distributions look like in spotify song pools?

We reshaped the data into long format so we would be able to plot the columns in one graph to create a more direct view. 32,828 tracks are included in this list Speechiness, Acousticness, Liveness, instrumentalness all skewed to the right, which indicated that most songs were designed or created with less presence of spoken words, less acoustic, less liveness and less instrumentalness - but is it true for music that are marked with a popularity rate more than 80?

We filtered out the tracks with popularity < 80, 500 tracks are included. Most songs were designed or created with less presence of spoken words, less acoustic, less liveness and less instrumentalness.

Once again we looked into the tracks with popularity equal and higher than 80. We found out that most popular songs were published after 2010, which is not long after spotify were founded, except for songs in rock genre. Rock music fans must still prefer the classic rock n roll or maybe that’s what playlist curators think they are

What is the secret behind the songs with top 100 popularity?

We have analyzed the general feature of all the songs and the tracks with popularity of 80 - 100. We then narrowed it to the top 100 songs in this dataset.The purpose of this analysis is to help playlist curator to select songs based on the acoustic feature so the playlist would be more likely to get discovered.

If a song’s energy >0.5, danceability > 0.4, speechines < 0.4, liveness < 0.25, acoustics < 0.6, it’s more likely for it to become a top 100 popular songs.

Playlist Analysis:

What genres and subgenres of playlists gain more attention?

There are 24 playlist subgenres. In top 10 most popular playlist subgenres, 5 are from “pop” genre.

Like a rank for playlist genre, this sequence for subgenre can also be utilized in homepage playlists selection. Besides, higher ranked subgenres can be recommended more for all users.

Multiple Linear Regression:

How to leverage computational model to predict popularity?

We use multiple linear regression models to help Spotify understand which elements the audience cares most about after variable selection. Then they can leverage this model to predict popularity for a new song and decide whether recommend this song or not. Besides, this model can provide rules for artists to create better and popular songs. In our best model:

Energy is the most influencing criteria, recommend that Spotify staff pay more attention to the level of energy when creating playlist.
Danceability (the musical positiveness conveyed by a track) is the highest positively related variables.

Results and Conclusion:

In general, we firmly believe that any type of music can gain attention and success and we encourage more musicians to create diverse music. Since the popularity will directly affect income, we hope our Multiple linear regression model can help music creators to achieve greater commercial success.