Posts Tagged age
Earlier this week we looked at how gender can affect music listening preferences. In this post, we continue the tour through demographic data and explore how the age of the listener tells us something about their music taste.
Where does the age data come from? As part of the enrollment process for most music services, the user is asked for a few pieces of demographic data, including gender and year-of-birth. As an example, here’s a typical user-enrollment screen from a popular music subscription service:
Is this age data any good? The first thing we need to do before we get too far with analyzing the age data is to get a feel for how accurate it is. If new users are entering random values for their date of birth then we won’t be able to use the listener’s age for anything useful. For this study, I looked at the age data submitted by several million listeners. This histogram shows the relative number of users by year of birth.
The first thing I notice is the curve has the shape one would expect. The number of listeners in each age bucket increases as the listener gets younger until around age 21 or so, at which points it drops off rapidly. The shape of the curve aligns with the data from this study by EMI in 2011 that shows the penetration of music streaming service by age demographic. This is a good indicator that our age data is an accurate representation of reality.
However, there are a few anomalies in the age data. There are unexpected peaks at each decade – likely due to people rounding their birth year to the nearest decade. A very small percentage (0.01 %) indicate that they are over 120 years old, which is quite unlikely. Despite this noise, the age data looks to be a valid and fairly accurate representation, in the aggregate, of the age of listeners. We should be able to use this data to understand how age impacts listening.
Does a 64-year-old listen to different music than a 13-year-old?
One would expect that people of different ages would have different music tastes. Let’s see if we can confirm this with our data. For starters, lets compare the average listening habits of 64-year-old listeners to that of the aggregate listening habits of the 13-year-old listener. For this experiment I selected 5,000 listeners in each age category, and aggregated their normalized artist plays to find the most-frequently-played artists. As expected, you can see that 64-year-old listeners have different tastes than 13-year-old listeners.
The top artists for the average 64-year-old listener include a mix of currently popular artists along with a number of artists from years gone by. While the top artists for the average 13-year-old includes only the most current artists. Still, there are seven artists (shown in bold) that overlap in the top 20 – an overlap rate of about 35%. This 35% overlap is consistent across all ranges of top artists for the two groups. No matter if we look at the top 100 or the top 1000 artists – there’s about a 35% overlap between the listening of 13- and 64-year-olds.
I suspect that 35% overlap is actually an overstatement of the real overlap between 13- and 64-year-olds. There are a few potential confounding effects:
- There’s a built-in popularity bias in music services. If you go to any popular music service you will see that they all feature a number of playlists filled with popular music. Playlists like The Billboard Top 100, The Viral 50, The Top Tracks, Popular New Releases etc. populate the home page or starting screen for most music services. This popularity bias inflates the apparent interest in popular music so, for instance, it may look like a 64-year-old is more interested in popular music than they really are because they are curious about what’s on all of those featured playlists.
- The age data isn’t perfect – for instance, there are certainly a number of people that we think are 64-years-old but are not. This will skew the results to artists that are more generally popular. We don’t really know how big this affect is, but it is certainly non-zero.
- People share listening accounts – this is perhaps the biggest confounding factor – that 64-year-old listener may be listening to music with their kids, their grand-kids, their neighbors and friends which means that not all of those plays should count as plays by a 64-year-old. Again, we don’t know how big this effect is, but it is certainly non-zero.
Let’s pause and have a listen to some music. First the favorite music of a typical 64-year-old listener:
And now the favorite music of a typical 13-year-old listener:
Finding the most distinctive artists
Perhaps more interesting than looking at how the two ages overlap in listening, is to look at how they differ – what are the artists that a 64-year-old will listen to that are rarely, if ever, listened to by a 13-year-old and vice versa. These are the most distinctive artists.
We can find the distinctive artists by identifying the artists in the top 100 of one group that fall the furthest in ranking in the other group. For example Skrillex is the 40th most listened to artist for the typical 13-year-old listener, but for 64-year-old listeners, Skrillex falls all the way to the 3,937 most listened to artist, making Skrillex one of the most distinguishing artist between the two groups of listeners. Likewise, Roy Orbison is the 42nd most listened to artist among 64-year-olds. He drops to position 4,673 among 13-year-olds making him one of the distinguishing artists that separate the 64-year-old from the 13-year-old.
We can use this technique to create playlists of artists that separate the 13-year-old from the 64-year-olds. Are you a 13-year-old, having a party and really wish that grandma would go to another room? Try this playlist:
Are you a 64-year-old and you want all of those 13 year-olds at the party to go home? Try this playlist:
We can also use this data to bring these two groups together. We can find the music that is liked the most among the two groups. We can do this by ordering artists by their worst ranking among the two groups. Artists like Skrillex and Roy Orbison fall to the bottom of the list since each is poorly ranked by one of the groups, while artists like Katy Perry and Bruno Mars rise to the top because they are favored by both groups.
Again, the confounding factors mentioned previously will bias the shared lists to more popular music. Nevertheless, if you are trying to make a playlist of music that will please both a 64-year-old and a 13-year-old, and you know nothing else about their music taste, this is probably your best bet.
Artists that are favored by both 64-year-old and 13-year-old listeners are: Bruno Mars, Taylor Swift, P!nk, Rihanna, Justin Timberlake, Katy Perry, Robin Thicke, Maroon 5, Lana Del Rey, Daft Punk, Beyoncé, Drake, Luke Bryan, Adele, Macklemore & Ryan Lewis, Miley Cyrus, David Guetta, Lorde, Jay-Z, Usher
We can sum up the differences between the two groups in this graphic:
Broadening our view
We’ve shown that, as expected, 13-year-olds and 64-year-olds have different listening preferences. We can apply the same techniques across the range of age demographics typically used by marketers. We can find the most distinctive artists for each demographic bucket. It is interesting to see the progression of music taste over time. For instance, it is clear that something happens to a music listener between the 25 to 34 and 35 to 44 age buckets. The typical listener goes from hipster (Lumineers, Vampire Weekend, The National), to old (Pearl Jam, U2, Bon Jovi).
It is interesting to look at the starting year for artists in each of these buckets to get a sense of how the artist’s own age relates to the age of their fans:
My take-way from this is that no matter how old you are, you don’t like the music from the 70s and the 80s so much.
Most homogenous Artists
We can also find the artists that are most acceptable across all demographics. These are the artists that are liked by more listeners in all of the groups. Like in the 13/64-year-old example, we can find these artists by ordering them by their worst ranking among all the demographic groups.
Most homogeneous artists: Bruno Mars, Rihanna, Katy Perry, Lana Del Rey, Beyoncé, P!nk, Jay-Z, Macklemore & Ryan Lewis, Daft Punk, Maroon 5, Justin Timberlake, Robin Thicke, David Guetta, Luke Bryan, Taylor Swift, Drake, Adele, Imagine Dragons, Miley Cyrus, Lorde
This is essentially the list of the most popular artists but with the most polarizing artists from any one demographic removed. If you don’t know the age of your listener, and you want to give the listener a low risk listening experience, these artists are a good place to start. And yes … this results in a somewhat bland, non-adventurous listening session – that’s the point. But as soon as you know a bit about the true listening preference of a new listener, you can pivot away from the bland and give them something much more in line with their music taste.
Rounding out the stats
There are a few more interesting bits of data we an pull out related to the age of the listener
Average number of artists in listening rotation
The typical 25- to 34-year old listener has more artists in active rotation than any other age group, while the 65+ listeners have the least.
Relative number of plays per user by age group
Likewise, the typical 25- to 34-year-old listener plays more music than any other category.
Tying it all up …
This quick tour through the ages confirms our thinking that the age of a listener plays a significant role in the type of music that they listen to. We can use this information to find music that is distinctive for a particular demographic. We can also use this information to help find artists that may be acceptable to a wide range of listeners. But we should be careful to consider how popularity bias may affect our view of the world. And perhaps most important of all, people don’t like music from the 70s or 80s so much.