Stephen Phillips used to be the boss of We Are Hunted, becoming a tech lead on Twitter #Music after the social network bought his startup. This week, he published a long and interesting blog post about new models for music discovery, which is well worth 10 minutes of your time. Among his points: whatever method a service uses to identify similar songs – experts, social listening history, acoustic properties or a mix of them all – “there is a quality ceiling of about 80%.
At best, one in five songs recommended are not considered a good choice by the listener. Worse still, different people select different songs as being the odd one out.” Phillips wonders if existing music discovery methods have been measuring the wrong thing: songs rather than listeners. “A simple question, ‘why do I like this song?’, proves to be very tough to answer. It reaches into the heart of the human experience. You soon find yourself learning about the physics of sound, the anatomy of the ear, the chemistry and neurology of the brain, evolution and psychology,” he writes. We’ll let him tell the rest of the tale via the link below.