Raisa V. Kostina

Place of work

Organization:
FSBEI of HE “Russian Timiryazev State Agrarian University”
Degree:
candidate of economic sciences

Author's articles(3)

Application of Logical Classification Algorithms for Predicting Student Dropout in Smart Educational Environments

17.11.2026

Annotation

this study investigates the application of decision trees for predicting student dropout and identifying academic risk factors based on Learning Management System (LMS) attributes. A logical classification algorithm searching for conjunctive patterns was applied to a dataset comprising 112 structural and behavioral features of student engagement. The decision tree model achieved an error rate of 4.12%. Key significant factors identified include the frequency of login gaps (40.3%), time since initial enrollment (16.8%), and the number of incomplete module directories (14.06%). Comparative analy...
more

Comparative Performance Analysis of Machine Learning Techniques for Pattern Detection in Student Psychological Well-Being

17.11.2026

Annotation

this paper focuses on the application of three data analysis techniques – decision trees, neural networks, and self-organising Kohonen maps – to identify internal dependencies in student psychological and academic well-being data. Based on the analysis of a dataset including student survey and academic records, the performance of these methods in classification and prediction is compared. The results emphasise the importance of method selection depending on the characteristics of the data and provide a basis for further research in the application of machine learning in educational psychology...
more

Rule-Based Machine Learning in a Hierarchical Framework for Assessing Academic Performance and Educational Quality

17.11.2026

Annotation

the article discusses important aspects of academic performance prediction, including early risk detection and informed educational decision-making. An automated decision tree learning method can efficiently analyze multiple educational indicators, automatically identify key factors, and improve the accuracy and interpretability of predictions. This research approach is a valuable tool for university administrators and educators, helping them to reduce academic failure risks and ensure the educational stability of students. The article aims to expand the understanding of the impact of behavior...
more