E EREACE
Back
Revenue with marginMusic / Record Label - Market Research and Product

Spot the Next Viral Song for a Record Label

More than 100,000 new songs are uploaded to platforms every day. The A&R (artist scouting) team at an independent label can only listen to about 300 a week and arrives late to emerging artists: by the time a song goes viral on TikTok, the major labels have already offered a contract. They want a radar that detects viral potential within the first 72 hours.

Estimated annual impact on EBITDA
+€2.25M
Independent label that signs 20 artists a year. Illustrative example with indicative figures: replace them with your own company figures.

Where the money comes from

Revenue from artists signed before the competition
+€1.80M
Lower advance from signing earlier
+€600k
System cost
-€150k
Annual EBITDA impact
+€2.25M
Adds profitReduces profitSystem cost

What to do now

  1. 1Weekly list of 300 prioritised songs for A&R.
  2. 2Measure how many of those detected end up going viral.
  3. 3Sign with staged contracts based on results.

For your committee

One page with the decision, the impact, the risks, the steps and the KPI to track.

The print dialog opens: choose "Save as PDF".

Watch out: more volume is not always more profit

Signing many one-song virals: promotion costs and advances are not recovered if the artist has no staying power. Combine viral potential with career signals.

KPI for the committee

Revenue per euro of advance and radar hit rate.

Detail for your data team

Proposed technique: Neural Networks (Deep Learning / CNN)

Why: The key information is in the audio: the hook, the production, the voice. Convolutional neural networks treat the spectrogram as an image and learn sound patterns that nobody can describe in a table. With 500,000 examples and pretrained audio models, it is the right approach.

Cost of getting it wrong: A false negative is a hit that the competition signs; a false positive is wasted A&R time (cheap). That is why recall is prioritised at the top of the list.

Data needed: Audio of 500,000 songs from the last 3 years, labelled as 'viral' (made it onto viral charts) or not.; Early signals from the first 72 h: plays, skips in the first 30 seconds, saves, uses in short videos.; Metadata: genre, duration, tempo, language, artist followers.

The Ereace system

Test decisions with synthetic people before you test them with real ones.

This tool helps you decide with numbers. Before you invest, understand, test and rehearse the decision with the people involved: your customers, your team or your committee.

Understand
QualiSynth

Before you invest, find out what your customers think, need or reject about the initiative.

Test
StrataSynth

Put the offer, the message or the journey in front of synthetic people who do not always follow the happy path.

Train
ArenaSynth

Rehearse the committee presentation or the vendor negotiation against synthetic decision-makers.

See all Ereace products

About this tool. It is free and made by Ereace, an AI-native product studio and human intelligence ecosystem: it connects real human signals, synthetic people and the systems built around them, so teams can understand, test and act on human behavior before decisions reach the real world. About Ereace

Comments or suggestions? info@ereace.es