Application of machine learning methods for analysis of UX/UI data from mass user surveys"

Abstract

The subject of this article is the application of machine learning methods to the interpretation of UX/UI data collected through mass user surveys on digital platforms. The paper explores the hypothesis that coordinated use of various classification models allows for the identification of behavioral patterns that hold predictive value for assessing users’ interactions with product features. The goal is to perform a comparative analysis of classification accuracy using real-world UX/UI survey data. The methodology includes data preprocessing, feature encoding, normalization, clustering, and training of six model types: decision trees, random forest, gradient boosting, multilayer perceptron (MLP), logistic regression, and k-nearest neighbors. Particular attention is paid to how these models perform on small-scale, mixed-type UX/UI datasets. The modeling results demonstrate that even with limited data, it is possible to uncover significant relationships between socio-demographic variables, user types, and feature usage. These findings suggest that machine learning can be a promising approach for analyzing user behavior, with the potential for further integration into decision support systems. This approach can be adapted to various domains where structured user data is available, including online education, healthcare, public administration, urban services, and internal organizational platforms.