Streaming services more likely to recommend songs by male musicians [report]

A new study from Utrecht University in the Netherlands claims that recommendations by streaming services could be unfair, prioritising songs by male artists.

Break The Loop: Gender Imbalance In Music Recommenders specifically points the finger at a ‘widely-used’ algorithm on streaming services including Spotify.

Writing in The Conversation about her study, Dr Christine Bauer and PHD candidate Andrés Ferraro said that as users listen to the recommended songs, the algorithm learns from these, and this creates a ‘feedback loop’.

Superstars such as Ariana Grande, Billie Eilish and Taylor Swift may have huge followings on streaming services, but the feedback loop wipes out exposure for lesser-known female artists.

“Our analysis of around 330,000 users’ listening behaviour over nine years showed a clear picture – only 25% of the artists ever listened to were female,” according to Dr Bauer, assistant professor of the university’s Human Centred Computing department, and Ferraro.

“When we tested the algorithm we found, on average, the first recommended track was by a man, along with the next six.

“Users had to wait until song seven or eight to hear one by a woman.”

The study noted that this is already of concern with past statistics showing low female presence in everything from charts to songwriter associations, and from festival bills to recording studios.

The problem is aggravated as streaming now makes up 80% of revenue in most major music markets, and 400 million music fans around the world subscribe to a service, the report noted.

The report said the feedback loop can be broken and exposure gradually given to female artists.

“We took the recommendations computed by the basic algorithm and re-ranked them – moving male artists a specified number of positions downwards.

“In a simulation, we studied how our re-ranked recommendations could affect users’ listening behaviour in the longer term.

“With the help of our re-ranked algorithm, users would start changing their behaviour.

“They would listen to more female artists than before.

“Eventually, the recommender started to learn from this change in behaviour.

“It began to place females higher up in the recommended list, even before our re-ranking.

“In other words, we broke the feedback loop.”

This would mean that more female artists and their music could be discovered.

But the report said the lack of data “beyond the gender binary is a massive obstacle, both for research as well as for taking action and making progress on a societal level”.