Analysis of Data Prediction Generate by Admission Student Application using Least Square Method

The number of applicants entering each department at STMIK Sumedang has increased and decreased from year to year. The data can be used to gain knowledge and learning by searching for stored patterns. One of them is to predict the number of registrants in the following year. STMIK Sumedang doesn't have that system yet. Objectives This study aims to apply and analyze the accuracy of the least square method to predict the number of prospective students. This method is very suitable to be used to predict the magnitude of variables in time series. The number of applicants entering each department is entered based on a period, namely Information Engineering, Information Systems, and Information Management. Existing data amounted to five time periods, consisting of five years of new student admission data. To calculate the error rate, mean absolute deviation, mean square error, and mean absolute percentage error is used. With prediction results for 2020 obtained, are 225 people for Informatics Engineering, 82 Information Systems, and 11 Informatics Management. Besides, the results of the measurement of forecasting suitability with these methods include Informatics Engineering as much as 0.79
^%
, Information Systems 0.8%, and Information Management as much as 3.4%. The results of this study prove that to predict the number of registrants on the admission of new students using the least square method.