Topic:
Using IMLS 2013 data Levi Bowles, data science professional, applied a "nearest neighbor" methodology to find peer libraries for an example library system. The nearest neighbor method is widely used across many fields. The factors matched on were population served, branches, funding per capita, visits per population.
For the full post visit http://www.datasciencenotes.com/2015/10/peer-group-determination-library-peer.html.