FRONT-END FRAMEWORK FOR BUILDING APPLICATIONS WITH ADAPTIVE USER INTERFACES USING MACHINE LEARNING METHODS

The article examines approaches to developing a front-end framework for creating web applications with an adaptive graphical interface that dynamically adjusts to the individual needs of users through machine learning algorithms. The relevance of the problem lies in the need to develop interfaces capable of simultaneously meeting the needs of different demographic groups, which requires flexibility in customizing the user experience (UX) and user interface (UI) of modern websites. Traditional interface design methods do not always account for the specific needs of each user, which reduces the effectiveness of interaction with the site. The article proposes an approach that utilizes reinforcement learning algorithms to analyze user interaction with the interface and automatically adapt the interface based on behavioral data. This enhances the accuracy of interface personalization and improves the overall user experience. The goal of the work is to develop a tool that enables the automated restructuring of the graphical interface of web applications based on individual user needs to improve their user experience. The research develops algorithms to optimize user interaction with web application pages and improve interface efficiency. The research results demonstrate the framework's ability to dynamically respond to user behavior, assess their level of interaction, and make informed decisions regarding interface parameter adaptation, which in turn helps developers to reduce amount of work needed to implement personalized interface by eliminating the need to manually develop website variants. Using this approach the estimated code base reduction is 40-50%. Keywords: adaptive interface, front-end, machine learning, user experience, web design.