Forecasting Roof Tile Production Using DMA and DES for Monitoring to Production

This research focuses on forecasting roof tile production trends for a leading company in Kebumen, providing actionable insights to enhance production management and streamline operations. By leveraging a comparative analysis of the Double Moving Average (DMA) and Double Exponential Smoothing (DES) methods, this study examines roof tile production data spanning 60 months, from January 2019 to December 2023, to generate accurate monthly production forecasts. The dataset includes <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$1,415,987$</tex> records, with additional data from January 2024 used to validate the model's accuracy. Forecasting performance was evaluated using the Mean Absolute Percentage Error (MAPE) metric. The analysis revealed that the DMA method, specifically with thirdorder smoothing, achieved an accuracy of 93.20 %, corresponding to a MAPE of 6.80 %. In contrast, with an optimized alpha value of 0.5, the DES method outperformed DMA with a MAPE of 2.40 %, translating to an impressive accuracy of 97.60 %. These findings highlight the DES method as the superior choice for periodic forecasting in the roof tile industry. It offers a robust tool for production managers to maintain operational stability and mitigate the risks associated with demand variability. By implementing DES, the company can ensure a more reliable and efficient production process, ultimately leading to improved decision-making and sustained competitive advantage.