Development and experimental evaluation of an information system for intelligent customer segmentation

Relevance. In the context of ongoing digital transformation of business processes, the demand for intelligent information systems capable of analyzing and processing large volumes of customer data is steadily increasing. One of the key directions in this field is automated customer classification using machine learning algorithms, which enhances the effectiveness of marketing strategies and decision-making processes. Object of research: customer classification processes in information systems utilizing machine learning methods. Purpose of the article: to design, implement, and evaluate the architecture of software components for an information system aimed at intelligent customer classification, taking into account scalability, performance, and classification accuracy requirements.Research results.The article proposes an architecturalmodel of an information system comprising modules for data collection, processing, and classification. A set ofsoftware components has been implemented, integrating machine learning algorithms such as logistic regression, decision trees, and support vector machines. Experimental research was conducted using a real-world dataset, demonstrating high classification accuracy and efficient system performance under limited computational resources. Conclusions. The developed information system ensures accurate customer classification and can be integrated into commercial analytical platforms. The research outcomes may serve as a foundation for further improvement of intelligent data analysis systems.