En
Register Log in

List of publications on a keyword: «machine learning»

  • Rule-Based Machine Learning in a Hierarchical Framework for Corporate Bankruptcy Prediction

    Conference Paper
    Strategies of Sustainable Development: Social, Law and External-economic Aspects
    Authors:
    Polina D. Cherniaeva, Ekaterina S. Almazova, Sergei I. Gorbachev
    Work direction:
    Экономика предпринимательства
    Abstract:
    This article explores the application of rule-based machine learning, specifically decision trees, for predicting corporate bankruptcy within a hierarchical framework. Using a dataset from the Taiwan Economic Journal (1999–2009), the study evaluates the economic performance indicators that critically influence financial distress. The decision tree model achieved an error rate of 1.6%, outperforming neural networks (2.67%) and Kohonen maps (2.98%). The most significant factors identified include Persistent EPS (22.4%), Working Capital to Equity ratio (20.1%), and Pretax Income to Capital (15.5%). The results provide a transparent, scalable tool for investors and creditors to mitigate financial risks.
    Keywords:
    machine learning, decision tree, hierarchical framework, economic performance, bankruptcy prediction, financial health
    Go 

  • Logical Classification Algorithm for Phishing Domain Detection in Cybersecurity Analysis

    Conference Paper
    Strategies of Sustainable Development: Social, Law and External-economic Aspects
    Author:
    Veronika I. Korshunova
    Work direction:
    Социально-экономические процессы в обществе
    Abstract:
    This study investigates the application of decision trees for detecting phishing domains based on URL attributes. A logical classification algorithm searching for conjunctive patterns was applied to a dataset comprising 112 structural and server-related features. The decision tree model achieved an error rate of 3.26%. Key significant factors identified include the quantity of slashes in the URL (40.3%), domain activation time (16.8%), and directory length (14.06%). The results confirm the high efficiency and interpretability of rule-based machine learning for cybersecurity threat mitigation.
    Keywords:
    machine learning, cybersecurity, phishing domains, decision tree, threat detection
    Go 

  • Comparative Performance Analysis of Machine Learning Techniques for Cardiovascular Disease Pattern Detection

    Conference Paper
    Strategies of Sustainable Development: Social, Law and External-economic Aspects
    Authors:
    Olesia O. Oleinikova, Ekaterina S. Almazova, Tatiana V. Soloveva, Sergei I. Gorbachev
    Work direction:
    Социально-экономические процессы в обществе
    Abstract:
    This paper evaluates the performance of three data analysis techniques-decision trees, neural networks, and self-organizing Kohonen maps-in identifying cardiovascular disease patterns. Based on a dataset of 1,328 patient records, the models were compared regarding classification accuracy for target variables and demographic attributes. The neural network achieved the lowest error rate for disease prediction (3.61%), while the decision tree showed robust performance (6.17%) with higher interpretability. The findings underscore the necessity of method selection based on data specificity and the trade-off between accuracy and transparency in medical diagnostics.
    Keywords:
    machine learning, data analysis, neural networks, decision trees, Kohonen maps, healthcare analytics
    Go 

  • Adaptive real-time machine learning: methods for combating concept deviation in flow data

    Conference Paper
    Modern educational process: psychological and pedagogical support, educational strategies
    Authors:
    Aleksandr S. Prudkii, Kristina E. Zhevlakova, Vladislav V. Kukartsev
    Work direction:
    Специфика предметного содержания обучения математике и информатике в современных условиях
    Abstract:
    The article explores modern approaches to adaptive machine learning in real-time environments, focusing on the problem of concept drift in streaming data. It examines the main methods for detecting and correcting data drift, which allow models to maintain accuracy when working with non-stationary information streams. The article analyzes online learning algorithms, adaptive threshold mechanisms, and incremental model update techniques. It also discusses the potential applications of these methods in monitoring, forecasting, and automation systems, as well as the challenges associated with computational complexity and processing delays.
    Keywords:
    adaptive machine learning, streaming data, concept rejection
    Go 

  • Creating an interdisciplinary project using digital technologies

    Conference Paper
    Education, innovation, research as a resource for community development
    Authors:
    Anzhelika V. Kudashkina, Elena L. Makarova
    Work direction:
    Современные технологии в образовании
    Abstract:
    The article discusses what interdisciplinary projects are and how they can be implemented in the educational process. It provides an example of such a project and shows how modern technologies can be used. The article concludes that generative AI can successfully handle tasks of simple and medium complexity, but it faces challenges when the complexity increases, especially when there are subtle dependencies and unusual conditions.
    Keywords:
    innovative methods, machine learning, digital technologies, creative thinking, scientific research, Interdisciplinary project, generative AI, integration of disciplines, project implementation, geometric proof, solving geometric problems, planimetry, and automated problem solving
    Go 

  • The principle of operation of recommender systems and their impact on people using YouTube as an example

    Conference Paper
    Relevant issues of management, economics and economic security
    Authors:
    Mark I. Tagirov, Aleksandr A. Ushakov, Olesia V. Tereshchenko
    Work direction:
    Менеджмент и его разновидности, диверсификация, маркетинг, ценообразование и логистика
    Abstract:
    This article analyzes YouTube's recommendation system and explores its architecture, which is based on a two-stage machine learning model, taking into account the implementation of self-learning methods, and its evolution in 2025. The article focuses on identifying and systematizing the risks associated with content personalization, such as the formation of "information bubbles," the impact on user behavior, and the promotion of radical content. Recommendations for mitigating the identified negative effects on users and developers are presented, based on current scientific publications and statistics.
    Keywords:
    artificial intelligence, machine learning, personalization, algorithms, addiction, YouTube, recommender systems, information bubble, large language models
    Go 

  • Identification of econometric models of simultaneous equations and control systems based on machine learning

    Book Chapter
    Effective development of the modern economy: problems and prospects
    Author:
    Alina M. Minitaeva
    Work direction:
    Глава 12
    Abstract:
    The chapter proposes a method for analyzing economic systems based on the use of a model of simultaneous equations and machine learning. The architecture of a fully connected neural network capable of reflecting the structure of a discrete-time control system and allowing the identification of a system of simultaneous equations is considered. A method for training a neural network is proposed that allows estimating the coefficients of a set of simultaneous equations. A method for forecasting a multivariate time series based on the estimated structural parameters of the system using a perceptron is presented.
    Keywords:
    machine learning, neural network, multivariate time series, simultaneous equations, discrete-time control system, perceptron, control system identification
    Go 

  • Using artificial intelligence to improve business efficiency

    Conference Paper
    Innovative approaches to management in economic, technical and legal systems
    Author:
    Inna G. Iglinskaia
    Work direction:
    Информационные технологии в управлении бизнесом
    Abstract:
    The article examines the role of artificial intelligence (AI) in improving the efficiency of business processes. In the context of rapid technological progress, companies are faced with the need to adapt to new realities, and AI is becoming a key tool for achieving competitive advantages. The main areas of AI application are analyzed, including automation of routine tasks, improvement of customer service, forecasting consumer behavior and optimization of resource management. Special attention is paid to examples of successful AI implementation in various industries such as finance, retail and manufacturing. The challenges and risks associated with the integration of AI into business, including issues of ethics and data protection, are also discussed. The article emphasizes the importance of a strategic approach to the introduction of AI technologies, as well as the need to train personnel to work with new tools. In conclusion, conclusions are drawn about the prospects of using AI to in
    Keywords:
    competitive advantages, machine learning, digital transformation, data analysis, personnel training, forecasting, artificial intelligence (AI), data protection, business efficiency, process automation, customer service, resource optimization, business innovation, AI ethics, strategic implementation
    Go 

  • INDUSTRY 4.0 TECHNOLOGIES: MACHINE LEARNING AND THE CUSTOMER RELATIONSHIPS MANAGEMENT

    Conference Paper
    The Topical Issues of the Humanities and Social Sciences: from Theory to Practice
    Author:
    Pavel V. Malyzhenkov
    Work direction:
    Содержание и технологии профессионального образования
    Abstract:
    The Fourth Industrial Revolution represents the latest transformation of means of production in the history of humanity. These innovations are built upon preceding technical progress, starting from the creation of the network itself, its evolution from static to social through the introduction of blogs, wikis, and web services, further enriching it with semantic data to facilitate inter-machine interaction, and culminating in its current state. This work provides an overview of the most interesting methods and approaches in applying artificial intelligence within Industry 4.0 to address the optimization of customer relationship management systems.
    Keywords:
    machine learning, CRM, Industry 4, enabling technologies
    Go 

  • Company’s value evaluation through modifying its capital structure with bonds and stocks issuance simulation using machine learning and statistical analysis approaches

    Conference Paper
    Relevant issues of management, economics and economic security
    Authors:
    Daria I. Nazarova, Natalia S. Semina, Leonid R. Nikulin, Iuliia S. Tsertseil
    Work direction:
    Анализ и прогнозирование основных тенденций современной экономики на макро-, мезо- и микроуровне
    Abstract:
    The present financial landscape is complexly woven with the interplay of financial instruments and technologies, reshaping the way companies manage their value. Financial instruments act as the cornerstone of capital structure, influencing cash flows and overall valuation. Meanwhile, financial technologies introduce innovation and efficiency via presenting unprecedented capabilities in assessing and forecasting the impact of these instruments on a company's worth. The ability to make timely decisions on resource allocation and capital raising is a key determinant of success in a rapidly evolving business landscape. Thus, the financial sector undergoes transformative changes, reshaping how companies navigate complexities and make informed decisions in an increasingly dynamic environment. The symbiosis of these elements is reshaping the future of finance, offering new avenues for creating and managing value in an interconnected world.
    Keywords:
    machine learning, Capital structure, securities, company value, simulation modeling, statistical analysis
    Go 

  • Bioheuristics: theory, algorithms and applications

    Book Chapter
    Bioheuristics: theory, algorithms and applications
    Authors:
    Sergei I. Rodzin, Iurii A. Skobtsov, Samer A. El'-Khatib
    Work direction:
    Авторская монография
    Abstract:
    The book examines the current state and problems of bioheuristics development, biographical and memetic algorithms, the issues of finding optimal solutions by trajectory algorithms and bioheuristics of multicriteria optimization. Ant and swarm bioheuristics, their features and modifications are presented. Hybrid formic and hypeuruistic swarm segmentation algorithms of complexly structured images are considered as applications. The monograph is interdisciplinary, it is addressed to masters and graduate students studying the theory and practice of creating intelligent information systems and technologies, as well as specialists in the theoretical foundations of computer science, software engineering, system analysis, information management and processing, information systems and processes, bioinformatics.
    Keywords:
    experiment, modeling, optimization, machine learning, bioheuristics, drift analysis, ant system, particle swarm, image segmentation, fitness function, evolutionary computation, NFL theorem
    Go