Forecasting Monthly Sales Using Single Exponential Smoothing: An Evaluation and Performance Analysis

Abstract

Micro, Small, and Medium Enterprises (MSMEs) have a strategic role in Indonesia's economy, contributing more than 60% to the Gross Domestic Product (GDP) and absorbing the majority of the national workforce. One of the MSME sectors that is growing rapidly is the food and beverage industry, including home cake shops. However, many MSME actors have not utilized scientific methods in business decision-making, especially in sales forecasting. In fact, accurate sales predictions are very important in managing production, raw material procurement, and operational efficiency. This study examines the performance of the Single Exponential Smoothing (SES) method compared to Holt's Linear Trend in predicting cake shop sales over the past two years. Based on the evaluation using MAE, RMSE, and MAPE, the SES model showed higher accuracy, with a MAPE value of 2.82%, lower than Holt's which reached 3.73%. These results indicate that a simple model like SES is better suited for sales data that does not have strong trends. These findings confirm that the selection of prediction models should consider the characteristics of the data, not just the complexity of the algorithms used.