This article examines the application of machine learning in the national economy. It describes the main concepts and methods of machine learning, including supervised, unsupervised, and reinforcement learning. Key areas of using this technology in the economy are analyzed, such as market trend forecasting, financial risk management, and economic data analysis. Special attention is given to the advantages of machine learning, including improved decision-making efficiency, process automation, and handling large volumes of data. At the same time, the challenges of implementing this technology are considered, such as the need for high-quality data, legal and ethical aspects, and the shortage of qualified specialists. The paper provides recommendations for developing machine learning infrastructure, investing in research, and training professionals, which can contribute to economic growth and increase the country’s competitiveness.

Materials and methods: Various methods and approaches to examine machine learning in the national economy were used in this paper. The main methods include an analysis of scientific literature, statistical data analysis, modeling using machine learning algorithms, and practical implementation of economic models with programming languages such as Python and machine learning libraries.

To analyze economic data, methods such as linear regression, decision trees, and neural networks were selected, as they effectively predict changes in key macroeconomic indexes such as GDP, inflation, exchange rates, and unemployment levels. Pandas, NumPy, Scikitlearn, and Matplotlib libraries were used as tools to process, analyze, and visualize the data. The research is based on data from official statistical agencies and financial institutions, including historical data on macroeconomic indexes, market trends, and financial risks. Methods of cleaning, normalization, and data transformation were used for data processing to improve model accuracy. The practical part of the study included the development of machine learning algorithms for predicting economic indexes. A linear regression model was used to forecast GDP growth, while more complex models, such as random forests and gradient boosting, were applied to analyze more intricate economic relationships. Thus, the use of modern machine learning methods in economics allows us to obtain accurate forecasts, identify patterns in economic data, and make strategic decisions based on objective analysis.

Conclusion. The application of machine learning methods in the national economy offers significant potential for improving economic analysis and decision-making. Through the use of advanced algorithms and tools, such as linear regression, decision trees, and neural networks, it is possible to effectively model and predict key macroeconomic indexes, including GDP growth, inflation, and financial risks. These methods allow for a more detailed and accurate understanding of economic trends and relationships, leading to better strategic decisions by governments, businesses, and financial institutions. By using modern technologies such as Python, Pandas, NumPy, and Scikit-learn, the research demonstrated the ability to process and analyze large volumes of economic data with high precision. Machine learning provides a valuable approach for predicting economic indexes, managing risks, and optimizing resource allocation. However, the effectiveness of these models depends on the quality of the data used, and there are challenges related to data completeness, model interpretability, and computational resources. In conclusion, machine learning is a powerful tool for enhancing economic forecasting and risk management. For its successful integration into national economic systems, countries must invest in research, improve digital infrastructure, and develop educational programs to prepare skilled professionals. The proper implementation of machine learning can contribute to rapid economic growth, more efficient decision-making, and a stronger competitive position in the global economy.

Problem statement. One of the urgent problems of industrial automation is that the operation of the few predictive maintenance systems available on the Russian market is usually based on the collection and analysis of equipment data without considering the joint impact of internal and external factors. In the current economic conditions, it is necessary to make a reasonable choice and apply new technologies of artificial intelligence for research and realization of basic principles of mismatch negativity potential, which will open new horizons for increasing efficiency and reliability of industrial automated systems of predictive or prescriptive maintenance of multistage technological processes. Modeling of automatic reactions to environmental changes and prediction of failures will allow to develop adaptive systems that will significantly reduce the risks of failures and accidents, as well as contribute to optimization of production resources and reduction of operating costs.

Purpose. To study the possibility of using artificial intelligence technologies to implement algorithms based on the potential of mismatch negativity (MMN) and the possibility of their application in industrial automated systems of predictive or prescriptive maintenance, as well as to develop a basic MMN algorithm and implement it in the Python programming language.

Results. An algorithm implementing the basic principles of mismatch negativity potential has been developed. The practical necessity of using such an algorithm, which is based on neurophysiological mechanisms of sensory information processing in the human brain, for detecting anomalies in the operation of industrial equipment caused by external factors such as temperature, humidity, vibrations, and electromagnetic interference was determined, which allows solving the following tasks of industrial automation: anomaly detection, modeling of environmental impact, optimization of operational processes, prediction of failures, adaptation to changes in the environment. The basic architecture of the automated system is proposed, which takes into account the need to use software algorithms of mismatch negativity potential. It consists of modules of data verification, model training, anomaly detection, predictive model, visualization and module of integration with other industrial information and automated systems. The paper also presents the program code for the implementation of the basic MMN algorithm in Python language.

Practical significance. The results of the study can be used to design industrial automated systems of predictive or prescriptive maintenance, in which accuracy and decision time play an important role.

The purpose of the study was to find ways to ensure the effectiveness of training of universal specialists in energy fields in the implementation of the concept of lifelong learning through a practice-oriented approach.

Research methods. To understand the current and future needs of the energy industry, especially in terms of the development of higher professional education, the study used the method of forecasting, direct survey of regional employers of energy enterprises, analysis of the needs of industrial partners in qualified specialists. The normative basis of the study was the Decree of the President of the Russian Federation Nо. 204 (2018) and the federal state educational standard of higher education in the direction of training 13.03.02 “Electric power engineering and electrical engineering”. The theoretical basis of the study is the model of the system of continuous professional education, adapted to the training of specialists for the energy industry. The joint use of these methods has formed a holistic approach to understanding the personnel problems of the power industry and the possibilities of the educational system in their solution.

Results. Based on the model of the system of continuous professional education and the results of the analysis of the labor market demand in the Republic of Karelia, a practice-oriented educational program for training specialists in the field of power engineering was designed and implemented. Employers are increasingly looking for specialists with universal skills, capable of solving both typical and non-standard tasks and ready for further training during their working life. Successful implementation of the developed educational program is based on the joint cooperation of energy sector employers and university lecturers. Integration of industry experience with theoretical knowledge, vision of the industry development prospects allowed industrial partners and the university to jointly ensure the successful implementation of the designed educational program, helping to solve the problem of deficit of qualified personnel in the energy sector of the economy in the regions of the Russian Federation. The article presents the experience of the Department of energy supply of enterprises and energy efficiency of Petrozavodsk State University in training bachelors for the energy sector of the economy. The article reveals the totality of all the components of the model of the continuous education system, which contributes to the training of a universal specialist in the field of energy. The integrative qualities of the model are demonstrated, including the possibilities to receive higher and additional professional education for university students, productive combination of study and work at enterprises, ensuring the effectiveness of training, which is achieved by involving industrial partners in the educational process and strengthening the motivational component of the learning process. The educational programs are supplemented with disciplines forming digital and engineering competences, integrative forms of training are introduced: training and profile practice on the basis of ElectroSkills, internships with part-time employment, project activities with the solution of real tasks of enterprises.

Conclusion. The authors have proposed and realized new approaches to the formation of professional skills required for university graduates. The key role of industrial partners’ participation in the educational process during the whole period of training is shown, the existing problems and difficulties in the implementation of practice-oriented approach in the training of specialists are outlined, the ways of eliminating the identified problems are proposed. The content and methods of step-by-step implementation of the practice-oriented educational program of training students of energy fields are demonstrated on specific examples.

The purpose of the study is to analyze existing methods and systems of career guidance, evaluate their advantages and disadvantages, and propose our own solution to this problem, taking into account existing developments in this subject area. For people choosing a job, the issue of career guidance remains relevant, problematic, and not fully resolved. Graduates of secondary educational institutions have particular difficulties in choosing a profession and in choosing an appropriate educational institution due to their little life experience. Currently, a significant number of methods and computer systems have been developed for career guidance purposes. However, the recommendations of a consulting psychologist are still considered preferable. Meanwhile, modern computers can store and process a huge amount of diverse information about the respondent and professions, analyze the trends of the profession market. Therefore, the improvement of career guidance systems, endowing them with artificial intelligence seems promising.

Materials and methods. Information on the subject area was collected by studying artifacts. During the analysis of existing methods and systems of career guidance, the methods of classification and systematization, induction and deduction were used. The method of describing the norms and requirements for a candidate-specialist were job descriptions and lists of necessary competencies and contraindications to the profession. To identify an individual’s predisposition to a specific type of activity, methods were used to diagnose the interests, inclinations, capabilities, psychophysiological abilities of respondents, testing attention, intelligence, creativity, temperament, etc. The comparison of personal characteristics and requirements in the created system is carried out by means of production rules and a genetic algorithm. Among the advantages of genetic algorithms are conceptual simplicity and wide applicability, resistance to dynamic changes in the environment and the ability to self-organization. The developed career guidance system was subjected to experimental studies.

Results. A genetic algorithm has been developed in which information about professions and information about the respondent are taken as the initial information for creating a new population: a) his knowledge, skills and abilities; b) his desires, inclinations, personal qualities. Based on these data, the initial population of professions is formed. As a result of crossing a pair of individuals from the parent population, a descendant is obtained whose chromosome consists of the genes of both parents. The selection of surviving specimens is based on the percentage of success in the development of each of the professions in the list and the fitness function. The developed algorithm was implemented in a software system. As experiments showed, the genetic algorithm successfully copes with the task of finding the optimal list of professions according to a given criterion.

Conclusion. The results of the study show that the use of genetic algorithms provides convenient mechanisms for introducing artificial intelligence methods into the field of career guidance, which improves the quality of recommendations for choosing a profession.

The purpose of the study. In educational institutions of the national regions of the country, bilingual education can acquire an important meaning in ensuring the quality of the educational process. Bilingual subject learning and mastering of subject knowledge by students in a certain area based on the interconnected use of two languages (native and state) is of not only educational interest. In this regard, the purpose of the paper is to study the bilingual portrait of residents of the Republic of Tuva, identify the need for bilingual teaching of students in computer science and the feasibility of including bilingual means and methods of teaching in their training, using the example of Tuva State University.

Materials and methods. To achieve the set goal, the following methods were used: the mental approach of N. Pak to substantiate the need for bilingual education of students living in national regions; the competence approach in designing and processing questionnaire questions; the inversion approach of D. Barkhatova in developing tools and methods for bilingual education in computer science. A set of complementary research methods was also used: theoretical (analysis of sources on the research problem, specification of data, generalization of psychological and pedagogical literature, comparison of data, deduction, substantive interpretation, analysis of results) and empirical (questionnaires, testing, processing and analysis of the obtained results).

Results. The definition of the bilingual portrait of the residents of the Tuva Republic, as well as the identification of the need for bilingual teaching of computer science to students of the Tuva State University was carried out using specially developed questionnaires. The analysis of the questionnaire data showed that the number of bilinguals in the Republic of Tuva is 82%, among the students of the Physics and Mathematics faculty of the University – 99%. The number of surveyed lecturers, students and parents who consider bilingual education in the Republic of Tuva important exceeds 70%. Thus, the development of bilingual education in the study of subjects at school and university is becoming not only possible, but also necessary. To determine the scientific and methodological directions for the development of bilingual teaching of computer science at school and university, samples of different options for presenting educational information in bilingual textbooks on the topic “Information theory” were developed. An expert survey and a questionnaire among students revealed the fact of preference for textbooks with a synchronous presentation of content in two languages.

Conclusion. The statistical data of the questionnaire survey allowed us to present a bilingual portrait of the residents of the Republic of Tuva in general, and the students of Tuva State University in particular. It should be noted that for a significant majority of students, Tuvan is their native language, and Russian is the language of study. The analysis of the questionnaire data shows the relevance and necessity of bilingual teaching of subjects at school and university. This position was expressed by a significant part of the respondents, including lecturers, parents and students. The results of the study allowed us to determine the most preferable format for presenting the content of educational bilingual resources in synchronous and “inverted” form. It is certainly necessary to develop research of the mechanisms of bilingual thinking and, on their basis, create methodological systems for bilingual teaching of subjects in schools and universities of the Republic of Tuva.

The purpose of the study is to identify key methodological principles for adapting of performance indexes of classical libraries to assess the pedagogical and educational effectiveness of electronic library systems in professional education, as well as to determine their practical significance for the formation of tools for analyzing the impact of digital resources on the learning process.

Materials and methods. The study used an integrated approach combining theoretical analysis and empirical methods. A systemfunctional approach was applied to formulate the advantages of electronic library systems (remote, fast, equal, easy ... access), which provided a comprehensive analysis of their impact on the educational process. The historical and analytical method was used to identify key performance indexes used in evaluating the activities of classical libraries, which made it possible to justify their adaptation to the conditions of the digital educational environment. The empirical analysis included the processing of statistical data provided by electronic library systems using information from administrative offices and open sources. The regulatory and legal analysis covered the study of state standards and the provisions of Federal Law No. 273-Federal Law “On Education in the Russian Federation”, which ensured the verification of the compliance of the electronic library systems’ functionality with established educational requirements. The comparative method was applied to compare traditional library performance indexes with new metrics determined by the specifics of the digital environment.

The results of the study demonstrate that despite the continuity of the main performance indexes from classical libraries, they are transformed and acquire a new quality in the digital environment. Metrics such as the number of registrations, the number of visits and requests, the number of bookings, bounce statistics, and search queries are becoming more detailed thanks to digital technologies. The adapted indexes allow for a more detailed approach to assessing the pedagogical and educational effectiveness of electronic library systems – the impact on the formation of professional competencies, support for learning continuity, and achievement of the federal state educational standard of higher education.

The conclusion emphasizes that the results obtained create a theoretical and methodological basis for the development of a comprehensive model for evaluating the effectiveness of electronic library systems, requiring further verification and in-depth study of the relationship between the use of electronic resources, students’ academic performance and the formation of professional competencies.