Statistical model aims to ensure that artists receive fair pay

Researchers at the Vienna University of Technology (TU Wien) have developed a statistical model in the form of an algorithm that detects fraudulent sales of music sold on the Internet with a high degree of reliability. This is intended to make the music industry more transparent and fair.

Until now, music labels and bands had to rely on the major music platforms passing on the correct numbers and transferring correct fees - a dispute that has plagued the music industry for years.

100 million observations analyzed

In order to correctly determine how often music tracks are clicked on large international platforms such as iTunes, Spotify or YouTube, the scientists from Vienna worked with the music distribution company Rebeat Innovation . For the anti-fraud tool to be developed, huge data sets with over 100 million individual observations from the music industry were analyzed.

The labels have already received statements showing how much sales were made and when. It was difficult to check whether this was true.

“Of course you can look at the sales figures over time and see if there are any anomalies. But that's of little use. We have found that the crucial information lies in the relative relationship between the sales figures of each provider,”

explains TU Vienna statistician Nermina Mumic.

System has a hit rate of 92 percent

According to the expert, if a song sells twice as often on one online platform as on another, then this ratio will typically not change abruptly. The sales figures develop almost in parallel - meteoric increases in click numbers on YouTube should normally also be accompanied by rapidly increasing download rates on iTunes. Everything else is suspicious.

“But that alone is not enough,”

says Mumic.

“The matter is even more complicated: there are weekly or monthly fluctuations that are completely normal.”

The statistical model must therefore distinguish the usual fluctuations from fraudulent data cheats.

“If you examine the data with the naked eye, you will find a lot of strange abnormalities at first glance, but many of them are completely normal. In order to distinguish statistically explainable irregularities from real errors or fraud, you need statistical tools that have not existed in this form before.”

To test the new statistical tools, some of the original data from the music industry was experimentally manipulated.

“Our software detected over 92 percent of the manipulations,”

says Mumic happily and adds:

“This is an extremely good rate and we believe we can improve it even further.”

The only way to reliably outsmart the software would be an agreement between all music providers worldwide to falsify all data in a precisely coordinated way - and that is extremely unrealistic.


If you enjoyed this post and value the importance of well-founded information, become part of the exclusive Mimikama Club! Support our work and help us promote awareness and combat misinformation. As a club member you receive:

📬 Special Weekly Newsletter: Get exclusive content straight to your inbox.
🎥 Exclusive video* “Fact Checker Basic Course”: Learn from Andre Wolf how to recognize and combat misinformation.
📅 Early access to in-depth articles and fact checks: always be one step ahead.
📄 Bonus articles, just for you: Discover content you won't find anywhere else.
📝 Participation in webinars and workshops : Join us live or watch the recordings.
✔️ Quality exchange: Discuss safely in our comment function without trolls and bots.

Join us and become part of a community that stands for truth and clarity. Together we can make the world a little better!

* In this special course, Andre Wolf will teach you how to recognize and effectively combat misinformation. After completing the video, you have the opportunity to join our research team and actively participate in the education - an opportunity that is exclusively reserved for our club members!


Notes:
1) This content reflects the current state of affairs at the time of publication. The reproduction of individual images, screenshots, embeds or video sequences serves to discuss the topic. 2) Individual contributions were created through the use of machine assistance and were carefully checked by the Mimikama editorial team before publication. ( Reason )