DecisionSupport System for Inventory Prediction using Fuzzy Tsukamoto Method (Case Study: UMKM Bayou Indonesia

Abstract

Bayou Indonesia, an MSME engaged in acrylic product manufacturing, faces overproduction issues due to manual production planning, leading to stockpiling and wasted resources. This study aims to develop a decision support system using the Fuzzy Tsukamoto method to predict production quantities more accurately by analyzing historical data such as orders, shipments, and final stock. Data processing is performed with fuzzy logic to generate reliable production forecasts for the upcoming periods. The novelty of this research lies in the real-world integration of the Fuzzy Tsukamoto method within a CodeIgniter-based web application, which is directly implemented in the MSME environment moving beyond the purely theoretical simulations of prior studies. The system significantly improves production planning accuracy, reducing manual errors (MAPE) from 21.5% to 8.7%, with an RMSE of 11.2 units. Furthermore, it helps decrease excess production discrepancies by up to 30% per month, raises prediction precision to 85%, and accelerates the decision-making process from two to three days to real-time. The resulting operational efficiency gains are estimated at 60–70%. These findings indicate that the system provides a practical solution for MSMEs to minimize overproduction risks, optimize resource usage, and enhance production planning through data-driven methods.