Development of an Android-Based Inventory Decision Support System Using Rapid Application Development

Abstract

Inventory management remains a significant challenge for many Micro, Small, and Medium Enterprises (MSMEs), particularly due to manual stock recording, delayed inventory updates, and inefficient purchasing decisions. Most existing mobile inventory applications focus only on inventory recording without providing analytical support for inventory replenishment. This study aims to develop an Android-based Inventory Decision Support System using the Rapid Application Development (RAD) method by integrating adaptive demand forecasting, Economic Order Quantity (EOQ), and Reorder Point (ROP) calculations into inventory management. The study employed a Research and Development (R&D) approach following the RAD phases of requirements planning, user design, construction, and cutover. Historical inventory transaction data were used to generate demand forecasts, calculate EOQ and ROP values, and automatically provide purchasing recommendations. Functional performance was evaluated using Black Box Testing, usability was assessed using the System Usability Scale (SUS), and forecasting accuracy was measured using Mean Absolute Percentage Error (MAPE). The developed application successfully integrated inventory management, forecasting, inventory optimization, and purchase recommendation features. Functional testing showed that all application modules operated correctly, while the system achieved an average SUS score of 82.5, indicating excellent usability. The forecasting model also demonstrated satisfactory prediction accuracy with a low MAPE value, enabling the application to generate timely reorder recommendations. The proposed system not only improves inventory recording accuracy but also supports intelligent inventory planning, helping MSMEs reduce stock shortages and optimize purchasing decisions.