Does Your Data Mean Anything? Maybe Notsomuch.
8 min read

Does Your Data Mean Anything? Maybe Notsomuch.

Hello, new and old readers of Penny Fractions! I didn’t expect my Billie Eilish newsletter to attract so much attention, but I welcome anyone reading for the first time. This newsletter arrives every Wednesday morning (EST) and offers, I’d say, a rather critical view of the music streaming business. You can check out its archive here and I do a Patreon to pay the copy editors that help with the project. If you enjoy this newsletter and cannot support the Patreon, then forwarding it to a friend or posting on social media is always appreciated. Anyway, let’s talk about artists, analytics, and audiences.


This week’s newsletter centers on Nancy Baym’s essay ‘Data Not Seen: The Uses and Shortcomings of Social Media Metrics’ which was published back in October 2013. I read the essay earlier this year (as readers know, I’m a big fan of Baym’s recent book Playing to the Crowd), which explored in great detail much of the skepticism I’ve held about digital metrics and the exalted status they’re given within the music industry. I wanted to explore where metrics fall short of the self-made entrepreneurial myth spun up by streaming platforms in their marketing of data dashboards but it also helps better contextualize the various ways data can be used.

Who is the Audience for Your Audience?

A central issue that Baym identifies regarding social media metrics—which in this newsletter I’m going to expand out to including streaming metrics and will note where they diverge—is that the value of this information varies dramatically depending on who is using the information. She writes:

In short, there is a gulf between audiences as they are constructed in academia and industry. Professional creators around whom audiences actually gather are the third category. They may seem to be industry, but may not frame their audience only as economic assets but also in more relational and ephemeral terms involving emotions and aesthetics. These constructions of audience cannot be assessed with the same economically motivated data or tools. Indeed, from the beginning of audience analytics, creative staff including copywriters and filmmakers have argued that a reliance on audience metrics conflicted with their sense of their work as art (Napoli, 2011).

The different ways of contextualizing data struck me since many discussions of music platform stats flatten creator and industry desires into one. The Spotify for Artists page right now says: “Over 200 million fans are waiting for you. Sign up to Spotify for Artists and make the most of your music.” Are there really 200 million fans out there for a single artist? Of course not. No, that is a number for advertisers and investors to know the company’s reach. Baym notes that while industry professionals can view audience metrics through a solely capitalist lens, creators might seek out information about their respective audiences that are not singularly driven by profit.

Earlier this year, in a two-part series called “Artist Education is the New Competition” (Part 1, Part 2), Cherie Hu looked at how various streaming platforms and distribution services are trying to better inform musicians about how to navigate this digital landscape. The explicit assumption is that artists should think of themselves as entrepreneurs and thus should try to understand the best ways of optimizing and potentially monetizing their careers. A concern with this line of thinking is that instead of empowering artists with new skills and resources, it instead further burdens artists with the requirement to understand numerous platforms and ways of parsing data, which isn’t at all a skillset aligned with being a musician.

This manifests in truly bizarre ways. Liz Pelly, in her CTM Festival talk earlier this year, pointed this out through Spotify’s Game Plan videos, which is a series devoted to envisioning the career of a musician, as it was born and nurtured by Spotify. The video “Treating Your Music Like a Business” makes the implicit idea of these platforms into explicit text by pushing forward this neoliberal redux of a century-plus old music industry where all musicians are in competition. The goal is to create a sense of isolation that forces artists to rely on platform data, rather than on their fellow musicians, to build a fanbase, tour, maintain music venues or, again, simply foster community.

Wait...Are the Numbers Even Good?

Prior to the internet, there were plenty of numbers for measuring a musician’s audience: fan clubs, concert sizes, mailing lists, etc. What Baym points out is that all of these were ways of measuring audience but the primary purpose was communication, not data research. There would certainly be overlap but the need for a mailing list is to tell fans about a musician, where following an artist on YouTube in a way performs that information backward. Where that fan is represented as a single addition to a visible number of subscribers, rather than first existing as someone ready to receive mail for fans.

It’s a small but crucial point to remember because the visibility of such stats on the digital platform warps the perspective that people hold vast audiences at their fingertips. Reality would show only a fraction of consumers is ready to receive that information, unlike those who buy a concert ticket, which does show a rather deeper commitment to an artist beyond pressing a single digital button.

This issue of fully comprehending how to use such information ends up becoming a rather explicit labor issue for musicians. Baym writes:

However magnificent it may seem to have so much data available and to be able to mobilize that material in different ways, the promises of big data are a mixture of real potential with uncritical faith in numbers and hype about what those numbers can explain (Boyd and Crawford, 2012; Bruns, this issue). To even begin to make sense of the data, people need expertise and skill as well as software and human resources.

This analysis runs counter to the way Apple Music or Spotify for Artists are often portrayed. The accepted norm is to give raw data to a musician and leave it up to them to capitalize on it. Baym’s interviews with musicians complicate that messaging since musicians are not trained data scientists, so accumulating more numbers just adds a new skill for these workers to have to learn. This is a trend that’s become more normalized throughout the decade, so when Daniel Ek delivers quotes like “We’ve never before been at a place in time where you could make as many informed decisions and understand your audience as well as we can do now as an artist,” it masks the fact that more weight is put onto musicians and their teams. Many artists can, and do, adapt to this new system or have people within their team to do it, but no amount of three-minute videos can help with what is effectively a new digital-first job created.

This lack of complete understanding, especially with new metrics being spawned every few months, makes it seem like the industry is always chasing a new arbitrary number. Spotify talks about its bullshit Monthly Listeners stat, Apple loves the equally horseshit pre-saves, and YouTube constantly talks about bulk quantity views, which are known at this point to be easily fabricated. The assumption that musicians must use their data and information creates a troubling feedback loop where these metrics that are mostly created for advertising, not really for measuring fan engagement, are how artists are told to measure their career trajectory. Thus, if an artist doesn’t have enough monthly listeners, it can look bad. When in reality, as Baym’s essay notes, that platform may not be where the artist’s audience is found.

Fans Not Data

Baym closes not with a dismissal of data but rather with a call-to-action for spending more time providing proper context to artists; not only on what is being recorded but also on the intended output of said information. What’s perhaps more important to me is what Baym wrote here:

A million followers may in some ways be less valuable than a single post. These forms of value are not accounted for in economically motivated data analyses, and efforts to encapsulate them within the language of economics miss much of what reaching an audience means to a creator.

The assumption is that all artists are small businesses and must find value from all of the disparate information available to them is a false choice. If musicians were truly empowered through data, then they should be able to use this information towards goals that are of their own making and not be forced to align with for-profit platforms. Thus, as phrases like “artist-centric” and other terms buzz around, it’s important to see where these phrases are originating from and who they are benefitting. This mirrors the musicians’ data conversation because these workers gain meaningful insight with each new unlocked box of numbers or it is just another to-do on an endless less of music labor

Unheard Labor

Last week, a collection of musicians put out an open letter for musicians pledging not to perform or work with Amazon, as long as the company continues to work with Immigrant and Customs Enforcement (ICE). So far over 1,000 musicians have signed the letter, which is pretty amazing. Hopefully, more artists continue to contribute but I wanted to mention a letter written by Katie Alice Greer, of the punk band Priests and Sister Polygon Records, about imagining how this could be the start of musicians finding and using their collective, rather than individualized voice. Yesterday, #NoMusicForICE twitter account even mentioned Tableau employees that walked off the job to protest the company's work with ICE, which was a great show of cross-industry solidarity.

Spotify is profitable once again as it cuts costs and adds cheaper plans - The Verge

Last year, I thought Spotify was going to have a solid 2019 because most of the disconcerting factors of growth stagnation, declining average revenue per user (ARPU), and increased competition wouldn’t be quite as big a concern for a couple more years. Thus, I can’t say I’m surprised that the company got its first profitable quarter while seeing growth in certain markets through discounts and reduced payout to musicians. All the more reason for musicians to make higher demands if this indeed can become the new normal for the company.

Record Labels Can Now Pay Spotify to Promote Artists on the Platform, Via Pop-Up 'Music For You' Alerts - Music Business Worldwide

Everything on Spotify is about to go on sale to the highest bidder. Personally, I’d love for there to be any kind of regulation that would prevent one of the biggest music streaming platforms from essentially becoming pay-for-play. Perhaps those old payola laws need to be dusted off.

Music Video Platform Triller Raises $28m with ‘Sights Set on Overtaking TikTok’ - Music Business Worldwide

I’ll gladly become a broken record over this topic but the xenophobia that reeks out of how American companies and press talk about TikTok is shameful. Triller is a marginal platform, and its chairman, Mahi De Silva, said this “As a U.S. company, Triller is laser-focused on the protection of our community from the prying eyes of nefarious parties or political agendas which has been a clear issue among our competitors,” is unnerving. An uninteresting video sharing platform that serves the goals of advertisers and copyrights holders trafficking in such nationalism makes sense...but is still disappointing.

The Teens Don’t Want to Love TikTok - The Outline

The other flipside of TikTok is that there is absolutely nothing really unique about TikTok compared to any number of other video-sharing applications from the last couple of decades. I know this stands against the media narrative of the company but perhaps it’s better to admit that technology is stagnating rather become enamored every four years with a new video-sharing platform.

German Buying Behavior Study Shows Listeners Love Streaming, But More Willing to Get Physical - Billboard

This is an amazing headline but also simply highlights the fact that people are perfectly fine with engaging with music in many forms without being relegated to the omnipresent streaming platform.

An Interview with Damon Krukowski - The Believer

I think this newsletter features at least one mention of all of my favorite thinkers in this particular space of digital music, so do read this interview. (Wait, Holly Herndon and Mat Dryhust, can’t forget about y’all!)