The music-recommending website Sage uses artificial intelligence to review one’s most favored and most hated band and gives suggestions that match the underground acts closest to those tastes.
Of course, working with the recommender can also elicit suggestions based on different shades of personal music partiality — not just most and least favorite. And it’s even able to group some similar-sounding artists together as the listener’s input. Still, taking a band each from the most extreme ends of one’s tastes and seeing the results is perhaps the most fascinating part.
It’s all the project of videographer and music curator Sunny Singh, the documentarian mastermind behind the punk concert video archive hate5six. He just happened to be a data scientist before he became the punk scene’s premier archivist. But does Sage really work? I wanted to find out.
For an example, I punched in that I like At the Drive-In but don’t like Slayer. That doesn’t represent my actual tastes — I just used those to test the system. The results returned disbanded D.C. post-hardcore act Q and Not U as my top suggestion with a 63.1 percent match, followed by Lungfish (56.3 percent), Cheap Girls (53.5 percent) and Bear vs. Shark (62.5 percent).
How does it do that? According to a very technical blog from 2017, when Sage first launched, the recommender analyzes what are called “graph embeddings” (the name literally stands for “Sage Analyzes Graph Embeddings”) through vectors it scans to “clearly define a taste profile and receive suggestions in a principled manner.” For the more technically and mathematically inclined, feel free to read more here.
“We’ve been able to leverage publicly available data about communal listening habits across over 200,000 bands and developed a novel model for finding new music,” Singh explained. “The model has been able to learn fairly robust mathematical representations of bands that preserves their ‘context’: bands that share members, have similar tempos, are lyrically and thematically related, tend to cluster together in the embedded space. This enables the user to define taste profiles capturing what they do and don’t like, and that corresponds to a well-defined set of mathematical operations on the embedded representations of bands.”
Ready to put it to the test? Try out Sage here.
2021’s Best Rock + Metal Albums (So Far)
Loudwire’s picks for the best rock + metal albums of 2021 so far
