Skip to content

A research paper co-written by Harrisburg University Information Systems Engineering and Management (ISEM) Ph.D. student, Nikesh Kumar Pahuja, and recent ISEM Master Degree Program graduate, Maria Helena Rivero, has been accepted for publication and presentation at a prestigious artificial intelligence conference.

The paper, “A data-Driven approach to efficient library management: Predicting library checkouts using Machine Learning,” will be published in SPRINGER NATURE – Research Book Series: Transactions on Computational Science & Computational Intelligence.

The conference the paper will be presented at, the 23rd International Conference on Artificial Intelligence, will take place in Las Vegas July 23-26

The paper abstract can be found below:

Library circulation facilitates the lending activities, including checkouts and renewals by patrons. This service consumes more extensive Library resources and is an area that could be improved by applying Machine Learning techniques. This study uses the Integrated Library Systems dataset from the Office of Chief Data Office City and County of San Francisco. This study builds a Machine Learning model to predict the total checkouts by patrons in public libraries in San Francisco, California, USA.

The study used fourteen predictors to train several Machine Learning models to predict the checkouts. The study trained and evaluated several Machine Learning models using 10-fold Cross-Validation (10-fold CV): Logistic Regression (LR), Decision Trees (DT), Random Forest (RF), Lasso Regression (LSR), Neural Network (NN), Support Vector Regression (SVR) and XGBoost (XGB). The model performance was evaluated using the R Square metric. The best predictive algorithm was the XGBoost model with an R Square score of 0.72 and std dev of 0.002. This study and the predictive model will allow libraries to predict the number of checkouts and renewals a patron will do in the future. It will allow libraries to manage their resources efficiently. The methods and models developed in this study can also be applied by other libraries on their data to manage their operations efficiently.

ABOUT HARRISBURG UNIVERSITY

Accredited by the Middle States Commission on Higher Education, Harrisburg University is a private non-profit university offering bachelor and graduate degree programs in science, technology, and math fields. For more information on the University’s affordable demand-driven undergraduate and graduate programs, call 717.901.5146 or email, Connect@HarrisburgU.edu.