Matt McVicar, Cédric Mesnage, Jefrey Lijffijt, Tijl De Bie. “Interactively exploring supply and demand in the UK independent music scene.” Machine Learning and Knowledge Discovery in Databases. Volume 9286 of the series Lecture Notes in Computer Science pp 289-292, 2015. (pdf)
(note: this page makes use of d3.js, which is supported by all “modern browsers”. This page is best viewed in Google Chrome)
This demo paper was presented in the 2015 European Conference on Machine Learning and Principles and Practice of Knowledge Discovery in Databases (ECML-PKDD).
The distribution of supply of (band density) and demand for (tweet density) 42 music genres can be seen below. Selecting a genre from the drop-down menu below will load 3 interactive maps (loading time should be only a few seconds).
First is the map for genre supply. This shows the number of independent UK music artists in every administrative region in the UK. Hover over a region to see the number of artists we know about per 1,000 population. Darker shades of green represent higher artist density for that genre.
Next, we show the genre demand for each region, quantified by number of Tweets about a given genre divided by region population. Hovering over a region shows the tweet density, with darker shades of purple indicating higher Tweet density.
Finally, we show the net supply and demand, which is a measure of balance between supply and demand in a given region (see paper for details). Neighbouring areas of high demand yet low supply (or vice-versa) offer opportunities for exploitation. For instance, an artist could arrange live concerts in a neighbouring county if their genre is in higher demand than in his own locality.
We hope you enjoy exploring the UK independent music scene!