Sales Trend Moment Prediction in Minimarkets Using the Moving Average and Trend Moment Methods

Abstract

This study aims to analyze and predict sales trend moments at a minimarket by utilizing simple yet effective statistical approaches, specifically the Moving Average and Trend Moment methods. Minimarkets, as part of modern retail, hold a strategic position in fulfilling the daily needs of communities. However, they often face significant challenges due to fluctuations in demand, particularly during special occasions such as Ramadan, Eid al-Fitr, Christmas, and New Year. These periods are characterized by sudden and substantial spikes in customer demand, which are difficult to predict accurately without proper analytical tools. Such unpredictability can lead to either overstocking or stock shortages, resulting in inefficiencies in operations and negatively impacting customer satisfaction. This research uses monthly sales data collected from a minimarket located in Medan over the past two years (January 2023 to December 2024) to build a prediction model. The model’s performance is evaluated using the Mean Absolute Percentage Error (MAPE), achieving a high accuracy level with an error rate of only 2.28%. The novelty of this research lies in the integrated application of the Moving Average and Trend Moment methods to forecast seasonal sales trends specifically for small-scale minimarkets. This approach, although simple, offers a practical and accessible predictive model that micro, small, and medium enterprises (MSMEs) can implement without the need for sophisticated or costly systems. Consequently, it provides valuable insights for optimizing stock management, budgeting promotional activities, and developing adaptive procurement strategies aligned with consumer behavior changes. Moreover, this study paves the way for future research by suggesting the exploration of advanced machine learning techniques and alternative evaluation metrics to handle more complex and dynamic sales data. Such advancements are expected to further enhance prediction accuracy, thus improving business planning and responsiveness to fluctuating market demands.