Intelligent Inventory Management in the Dairy Industry: A Model of Optimization and Automation using EOQ and Machine Learning

Inventory management is a fundamental pillar for the proper functioning of any company; therefore, an adequate inventory management will allow optimizing resources and reducing costs; however, a deficient management would end up causing economic losses that affect the profitability of the company. For this reason, the purpose of this research is to estimate the real future demand and calculate the optimal order quantity by using algorithms and programs based on machine learning, in order to automate inventory management. For this research, data were collected from the company context of study in the dairy industry, specifically the historical sales records of 2023 and 2024. The "5 Whys" methodology was used to identify the root causes of the problems detected. In addition, mathematical models such as Economic Order Quantity (EOQ), Reorder Point (ROP) and Safety Stock (SS) were used, together with Python programming, highlighting the use of the SARIMAX model to analyze temporal and seasonal patterns typical of the dairy industry. This approach made it possible to project an annual demand of 36,463 units of cheese and reduce the time to place new orders to 35 minutes. In addition, the implementation of machine learning improved the accuracy of manual calculations by 7.74% and reduced monthly sales losses by $1,698.42. Machine learning plays a key role in the automation and accuracy of inventory management, helping to improve business profitability.