back Back

How to identify hit songs with 97% accuracy, using machine learning

Jun. 21, 2023.
2 min. read Interactions

"Neuroforecasting" applies machine learning to neurophysiologic data.

About the Writer

Amara Angelica

161.29523 MPXR

Amara Angelica is Senior Editor, Mindplex, and formerly Editor, KurzweilAI

Credit: Pixabay

Every day, tens of thousands of songs are released. This constant stream of options makes it difficult for streaming services and radio stations to choose which songs to add to playlists, says Paul Zak, a professor at Claremont Graduate University.

Zak is senior author of a study published in Frontiers in Artificial Intelligence, where he offers a solution: “neuroforecasting”—applying machine learning to neurophysiologic data.

Neural data

In the study, participants listened to a set of 24 songs, and were asked about their preferences and some demographic data.

During the experiment, the scientists measured participants’ neurophysiologic responses to the song. A wearable watch provided heart rate data, which was used to infer neural states from activity of the cranial nerves (based on downstream effects of dopamine and oxytocin), as noted in JeŽová et al., 1985Zak, 2012Barraza et al., 2015

Machine learning

“The brain signals we’ve collected reflect activity of a brain network associated with mood and energy levels,” Zak said. This allowed the researchers to predict market outcomes, including the number of streams of a song.

The researchers found that a linear statistical model identified hit songs at a success rate of 69%. But when they applied machine learning to the data they collected, the rate of correctly identified hit songs jumped to 97%.

“That the neural activity of 33 people can predict if millions of others listened to new songs is quite amazing. Nothing close to this accuracy has ever been shown before,” Zak said.

“If in the future, wearable neuroscience technologies, like the ones we used for this study, become commonplace, the right entertainment could be sent to audiences based on their neurophysiology, ” Zak said.

But the researchers pointed to some limitations. For example, they used relatively few songs in their analysis. And the demographics of the study participants did not include members of “certain ethnic and age groups.”

Citation: Merritt, S. H., Gaffuri, K., & Zak, P. J. (2023). Accurately predicting hit songs using neurophysiology and machine learning. Frontiers in Artificial Intelligence, 6, 1154663. (open-access)

Let us know your thoughts! Sign up for a Mindplex account now, join our Telegram, or follow us on Twitter

Comment on this content


2 thoughts on “How to identify hit songs with 97% accuracy, using machine learning

  1. dopamine levels
  2. I would love to have a service that also inputs my personal biofeedback for song selection so that I have an intelligent way to use music functionally for different purposes. Even further, it might have an continuously evolving approximate knowledge, for example, of my historical dopamine levels so that it could optimize towards a healthy pleasure-pain balance and help avoiding addictions, burnouts and other undesired mental states. There are quite a bit of potential cool applications and some of them generate data even with biomedical implications so that individuals may get rewarded for such contributions. Great power of music indeed.


💯 💘 😍 🎉 👏
🟨 😴 😡 🤮 💩

Here is where you pick your favorite article of the month. An article that collected the highest number of picks is dubbed "People's Choice". Our editors have their pick, and so do you. Read some of our other articles before you decide and click this button; you can only select one article every month.

People's Choice