Libraries play an important role in supporting academic activities by providing access to information, learning resources, and research materials. To improve the quality of library services, it is necessary to understand visitor attendance patterns and estimate the number of visits in future periods. This study aims to forecast library visitation at UMSU using the Linear Regression and Trend Moment methods, and to compare the accuracy of both methods using Mean Absolute Percentage Error (MAPE). Historical visitation data were used as the basis for the forecasting analysis. The results show that the Linear Regression method produces a forecast value of 1.65 for the next period with a MAPE value of 4.59%, while the Trend Moment method produces a forecast value of 1.77 with a MAPE value of 5.86%. Based on the comparison of MAPE values, Linear Regression provides better forecasting accuracy than the Trend Moment method because it has a lower error rate. Therefore, Linear Regression is considered more suitable for forecasting library visitation in this study. These findings are expected to support library management in service planning, resource allocation, and the improvement of data-driven decision-making.
Copyrights © 2026