Prediction Of New Students Using The Exponential Smoothing Method (Case Study: STMIK Kaputama)

Abstract

With this prediction system for the number of new students, it functions to determine the priority of how many new students will be accepted in the following year. For each new teaching according to the factual and quite accurate new student data reports by implementing a computerized system, the data processing will be more precise and reduce errors in predicting it. This prediction will provide an overview based on the trend of the number of new students at STMIK KAPUTAMA. The method used is the exponential smoothing method by looking for how big the error is with different alpha values, namely 0.1 to 0.9. Each alpha tested will give different results. The purpose of the above calculation is to find out (a) alpha which produces the smallest forecast error. By taking data on the number of new students in the previous period, forecasting by determining the value of weight (a) alpha. The value of weight (a) alpha depends on the number of new students, where the nature of this forecasting determination of the value that is closest to the actual conditions. The forecasting results above are the closest to the overall number of new students alpha 0.9 is 1,207.9 and forecast error is 15.75.