Machine learning algorithm helps researchers identify hit songs with 97% accuracy

US researchers used a complex machine learning technique to analyse brain reactions and were able to predict music hits with 97% accuracy.

Here's What We Know

Researchers equipped study participants with special sensors and let them listen to a set of 24 songs. They were also asked about their musical preferences and gathered some demographic data.

During the experiment, the scientists measured the participants' neurophysiological responses. According to the scientists, they were able to record brain activity related to mood and energy levels.

After collecting the data, the researchers used different statistical approaches to assess the effectiveness of predicting neurophysiological variables. They used a machine learning model to improve accuracy.

As a result, the linear statistical model identified hit songs 69% of the time. When they applied a machine learning model, the accuracy increased to 97%.

According to the scientists, their research could help streaming services identify hit songs and build personalised playlists more effectively.

They also believe the approach could also be used to predict the success of other entertainment products, such as films and TV shows.

Source: TechXplore