I have always believed (and still do believe) that circulation data holds loads of latent information that can be used to improve services to our users. This includes using it as input for recommender systems; however, there are some caveats when you are thinking of using circ data as the basis for recommendations:
- All non-circulating items would be excluded from recommendations
- Recommendations would be influenced by the availability of the materials to be loaned. For example, items that are in high demand, but are available in one (or few) copies would be ranked lower than less interesting books which are available in more copies, because library users have the tendency to check out whatever is currently available to them.
For more, see http://www.dlib.org/dlib/may08/monnich/05monnich.html
--------------------------------------
Kevin M. Kidd, MA, MLIS
Library Applications & Systems Manager
Boston College Libraries
Phone: 617-552-1359
Fax: 617-552-1089
e-Mail: kevin.kidd_at_bc.edu
Blog: http://datadrivenlibrary.blogspot.com/
Received on Wed May 21 2008 - 09:43:43 EDT