Development of An Ai-Driven Web Application For Business Process Optimization In Product-Oriented Enterprises

This paper presents the development of an AI-driven web application designed to optimize business processes in companies engaged in the production and commercialization of goods. The system provides comprehensive traceability across purchasing, inventory, production, and sales workflows, integrating classical machine learning algorithms to support strategic decision-making. The project followed a phased methodology: first, a comparative analysis of Python-based algorithms was conducted to select suitable models for prediction and classification tasks. Next, data collection was systematized through user-friendly web interfaces, enabling the identification of key variables for training models focused on forecasting demand and segmenting customers and suppliers. Finally, functional testing validated the effectiveness of the application and its embedded algorithms. The resulting cloud-based platform leverages linear regression, logistic regression, k-nearest neighbors (KNN), and decision trees to enhance operational efficiency and decision accuracy. This work demonstrates the potential of combining web technologies and artificial intelligence to support data-driven management in commercial enterprises.