Measuring the accuracy of Short Moving Average (SMA) forecasting performance with 3 medium data ranges

Abstract

The Short Moving Average (SMA) forecasting method is one of the most widely used forecasting methods, especially for processing data with low and high levels of variation and is not linear over time. However, the opportunity to develop and improve forecasting performance using the SMA method is still wide open. The performance of a forecasting method can be seen from the error distribution. One of the steps to calculate the SMA forecasting value is to determine the forecasting range. The length or shortness of the forecasting range can determine the accuracy of the SMA forecasting value. Therefore, in this study a comparison of SMA forecasting results was carried out using 3 different medium forecast ranges. The next step is to compare the error values, namely those that produce the smallest Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE) values. From the research results, it can be seen that the SMA forecasting performance using the shortest range has the smallest error value when compared to SMA forecasting using other forecasting ranges.