Interpretable analysis of public library service outcomes based on ensemble learning models: Data study from China (2007–2021)

Abstract

Service outcome is a crucial component in the overall evaluation of public library service efficiency. Specifically, identifying and analyzing key factors that influence public library service output precisely can provide a significant theoretical basis for rational library resource allocation planning. Utilizing 15 years of data from the National Bureau of Statistics of China, the research predicted library service outcomes based on resource inputs. To achieve high predictive performance, six ensemble learning models were trained and evaluated, with CatBoost selected for its superior performance. Additionally, SHAP interpretability method was applied alongside CatBoost to offer nuanced insights into the influence of various factors, from both holistic and local perspectives. The research not only provided concrete suggestions for enhancing public library service outcomes but also introduced new approaches for processing and analyzing data in the field of library science.