Reorienting Collection Analysis
Cost-Effective Item-Level Analysis and Machine Learning in Public Libraries
Keywords:Public libarary, Machine Learning, Collection analysis
In public libraries, especially those in rural settings, it is important that every dime of library funding is leveraged effectively into serving the community. As part of a year-long project beginning in January 2023, we are evaluating item-level cost-effectiveness for each circulating item housed at the public library in Lakeville, Indiana. Through the use of big(ish) data, some custom Python scripting, and machine learning algorithms we hope to answer: How much money is saved by library patrons through their use of the public library's physical collection? How much money is saved by the community through the operation of a public library based on the use of the circulating collection? And are there any non-obvious traits which make an item or title a more or less cost-effective circulating asset? In this column, I will describe the scripts, share initial findings, discuss challenges, and investigate next steps.
How to Cite
Copyright (c) 2023 Ross Hanney
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
Authors that submit to Information Technology and Libraries agree to the Copyright Notice.