<![CDATA[Micro, small, and medium enterprises (MSMEs) in the service sector, particularly boarding house and laundry businesses, often face challenges in managing operational data in an integrated and structured manner to support effective decision-making. In practice, most business owners rely on fragmented records and experiential judgment, resulting in limited ability to identify operational patterns and optimize business performance. This study proposes the design and implementation of a lightweight data management pipeline based on Extract, Transform, Load (ETL) and a data mart using a semi-Kimball approach to support Business Intelligence in MSMEs. The research adopts a Design Science Research (DSR) methodology, focusing on the development of a practical system artifact. The dataset consists of a combination of internal operational data, data from similar businesses, and simulated data reflecting realistic operational conditions. The system is implemented using Python for ETL processes, SQLite as a lightweight data warehouse, and Flask for backend and API services. The results demonstrate that the proposed system successfully integrates multi-source data—including occupancy, laundry transactions, and operational activities—into a structured and consistent data model. The system further enables the delivery of interactive dashboards that support descriptive and diagnostic analytics, facilitating the identification of operational patterns and improving data-driven decision-making.]]>
Copyrights © 2026
