A visual analytics oriented decision support system for inventory management operations

The growing importance of data-driven decision-making processes today has increased the need for advanced systems that enable decision-makers, who must make decisions under competitive and time pressure, to easily interact with data. Inventory management is a quantitative process that includes demand forecasting and EOQ (Economic Order Quantity) calculations. This study aims to develop a decision support system that incorporates data automation and artificial intelligence integration for the effective management of these operations. The system uses Power BI, Python, and Prophet to generate demand forecasts, export the results to Excel, and automate the projected calculations. In addition, an artificial intelligence language model has been integrated via Power Automate to enable users to interact with the analysis outputs in natural language. All results are presented to decision-makers through an advanced dashboard system based on Power BI. The system has reduced the workload by automating demand forecasting and total cost calculations, ensuring accuracy and repeatability, and supporting decision-making processes through large language model-based software and visual dashboards. The work offers a user-friendly and low-cost digital transformation model that combines data analytics, predictive modeling, operational calculation, and artificial intelligence in a single system, providing a unique contribution to businesses aiming for competitive decision-making processes.