Airplay Live has identified audio features statistically associated with how well songs retain an online radio audience, based on tests at two stations. The association appeared in the songs’ early plays, according to the Helsinki-based company.
Developed by Helsinki Underground Ltd, Airplay Live measures whether songs and talk topics hold a station’s online audience or lose listeners. It tracks the station’s live listener count alongside its now-playing data at one-second intervals, then compares audience movement during each play with the station’s usual movement at that time. Repeated plays build a station-specific score for how reliably each song holds listeners.
The audio signal emerged as a byproduct of research into how those scores settle as plays accumulate. Airplay Live says it derives the signal from the audio itself, without using data on listener responses to the song being analyzed. It is continuing the research before deciding whether to make the audio analysis a product feature, with potential applications in radio music programming and music production.
The company has separately tested its listener-hold method for repeatability, schedule bias and false signals. Results and known limitations are published at airplaylive.com/controls. The audio findings’ charts and methodology are available at airplaylive.com/audio.
“We wanted to know whether a song actually keeps listeners on the station, not whether someone remembers liking it,” said Timo Salonen, founder of Helsinki Underground. “The station’s own audience already answers that question every time a song plays. We just had to find a way to measure it.”
Airplay Live applies the same framework to talk, transcribing broadcasts and grouping recurring topics and mentions to show which subjects hold listeners as evidence builds across broadcasts. Results are specific to each station. Stations can request pilot access; setup requires a reliable concurrent listener count and a now-playing feed.
These stories might interest you
Nine takeaways from ARN’s digital transformation
