2782-6333 3 9 2023 1-85

RAR RUS 8-20 Volgograd State Technical University, Volgograd Lomakin Nikolai 0000-0002-6849-4313 Peter the Great St. Petersburg Polytechnic University, St. Petersburg, Russia Kulachinskaya Anastasia 0000-0001-9932-9866 Volgograd State Technical University, Volgograd, Russia Naumova Svetlana 0009-0003-4374-8625 Volgograd State Technical University, Volgograd, Russia Ibrahim Maya 0000-0002-3895-8930 Volgograd State Technical University, Volgograd, Russia Fedorovskaya Evelina Volgograd State Technical University, Volgograd, Russia Lomakin Ivan Modelling Profits Forecasts for the Russian Banking Sector Using Random Forest and Regression Algorithms This study is relevant because market uncertainty induces progressively more attempts at making accurate profits forecasts in the banking sector. The scientific novelty of this study lies in the profits forecasts for the Russian banking sector performed using a random forest machine learning (ML) model and a neural network regression model. Regarding technology, the two models are combined into a cognitive model, as they are executed in the same cloud service (Collab) and have a common dataset comprising a training set, scripts and result output. The aim of the study is to build two models: a random forest ML model and a neural network regression model. The dataset used in the random forest ML model and the regression model included data on the performance of the Russian banking sector and some macroeconomic data on the national economy and the stock market for the period 2017–2021. Specifically, the dataset for the models included the following: key rate (%), growth assets (%), overdue loans (%), gross domestic product (GDP, in billions of rubles), RTS index (points), USD rate (vs. RUB), investments in assets to GDP (%), exchange robots (%), capital outflow (in billions of rubles), bank assets (in trillions of rubles), stock accounts (pcs.), and bank profits (in billions of rubles). The practical relevance of this study is evidenced by the fact that the results of the digital profits forecasting for the Russian banking sector can be recommended for real-world use. In building the cognitive model, we used the Python language in the Collab cloud environment. The mean absolute error of the test set for the random forest ML model (DecisionTreeRegressor) was 414.67, which is 61% lower than for the linear regression model (LinearRegression), which had a mean absolute error of 667.65. 10.48554/SDEE.2023.3.1 368.519.86 digital model cognitive model ML model random forest profits forecast for banking sector https://sustainable.spbstu.ru/article/2023.9.1/ 1.pdf

RAR RUS 22-33 0000-0002-0630-7949 Lobachevsky State University of Nizhny Novgorod, Nizhny Novgorod, Russia Yashina Nadezhda 0000-0002-7256-4628 Lobachevsky State University of Nizhny Novgorod, Nizhny Novgorod, Russia Kashina Oksana 0000-0002-7182-2808 Lobachevsky State University of Nizhny Novgorod, Nizhny Novgorod, Russia Yashin Sergey 0000-0002-8924-2991 Lobachevsky State University of Nizhny Novgorod, Nizhny Novgorod, Russia Pronchatova-Rubtsova Natalia Methodology of Financial Monitoring Based on Cluster Analysis for the Implementation of National Projects in the Russian Regions The need to take into account imbalances among regional indicators in the development of state policy for financing national projects makes it necessary to develop a methodology that will enable objective assessment of the effectiveness of socially significant projects in Russia. This paper reports the development of a methodology for financial monitoring of national project implementations in the constituent entities of the Russian Federation, taking into account the correlation of their target indicators and using cluster analysis and methods in mathematical statistics. The proposed methodology was tested on health and demography national project data obtained from the Federal Treasury of Russia, the Federal State Statistics Service and the Accounts Chamber for 2020–2021. The analysis of public funding for national projects based on centralization indices and target indicators for their implementation enabled classifying the regions of Russia according to the levels of effectiveness and the financial risks of implementing the projects. The results of the study correspond to the actual effectiveness of national projects and can be used in the development of flexible state policy in financing national projects, taking into account the level of the target indicators achieved. 10.48554/SDEE.2023.3.2 332.1 national project target indicators cluster analysis financial monitoring https://sustainable.spbstu.ru/article/2023.9.2/ 2.pdf

RAR RUS 34-47 Peter the Great St.Petersburg Polytechnic University, Russia Victorova N. Natalia Peter the Great St. Petersburg Polytechnic University, St. Petersburg, Russian Federation Karpenko Pavel 0000-0002-5417-6648 Russian-Armenian University, Yerevan, Armenia Voskanyan Mariam Systematisation of Drivers for the Development of Socioeconomic Systems The Russian economy’s recovery processes during the postcrisis period are accompanied by clear heterogeneity in the development of regional socioeconomic systems. Domestic researchers note that over the past twenty years, the level of regional competition for both labour and financial resources has increased. For example, in the Russian Federation, in the period from 2011 to 2018, the number of labour migrants within the country increased by 1.59 times from 1894.1 thousand to 3,004.2 thousand people (although the 2018 figure decreased by 3% to 2928.0 thousand people in 2019), and the inflow of foreign investment for the period from 2011 to 2018 decreased by 40.4%. At the same time, in 2018, the largest share of foreign direct investment accounted for by the Central Federal District was 60%. Differentiation of regional development is complicated not only by economic, but also by natural, ecological, ethnic, political and other factors. In this regard, the role of a competent economic policy at the regional level is increasing, the main goal of which should be the sustainable development of territories in conditions that change under the influence of these factors. Thus, ‘the implementation of an effective regional policy in the context of the overall development of the country’s economy is impossible without an analysis of regional specialisation and concentration of production in the country’. Therefore, the purpose of this study is to analyse the theoretical foundations for determining the specialisation of regional socioeconomic systems and the formation of a classification of factors influencing the development of regional socially significant systems. The study is based on the scientific works of Russian authors in the field of competitiveness, regional differentiation, the geoeconomic position of a region and its economic independence and development prospects. 10.48554/SDEE.2023.3.3 332.142 regional competitiveness specialisation formation factors the regional differentiation problem sustainable regional development https://sustainable.spbstu.ru/article/2023.9.3/ 3.pdf

RAR RUS 49-65 0000-0002-5649-1799 Peter the Great Saint Petersburg Polytechnic University, Saint Petersburg, Russia Kokh Yulia Developing technologically innovative industrial infrastructural facilities for their better efficiency: case study of technology parks in Russia The article discusses an approach to forming a model for evaluating the efficiency of a typical technologically innovative industrial infrastructural facility using a nonparametric modelling. The study models and measures the efficiency of technologically innovative industrial infrastructure (case study of technology parks in Russia) by using a data envelope analysis (DEA) method. Facilities are identified as efficient or inefficient from the standpoint of the DEA methodology, and the evaluation results are compared with the results obtained in the Technopark National Ranking. The article also presents recommendations for making technologically innovative industrial infrastructural facilities more efficient in accordance with the results of the modelling; it substantiates the mechanism of ensuring the competitiveness of technologically innovative industrial infrastructural facilities of the same type, based on the technical efficiency achieved by a facility, as a result of solving an optimization problem using the shell data analysis method. 10.48554/SDEE.2023.3.4 005.5 technologically innovative industrial infrastructure development of innovative infrastructure technical efficiency data envelope analysis https://sustainable.spbstu.ru/article/2023.9.4/ 4.pdf

RAR RUS 67-85 W-8013-2019 57203897426 0000-0002-9703-5079 Peter the Great St. Petersburg Polytechnic University, Russian Federation Gintciak Aleksei gintsyak_am@spbstu.ru 0000-0002-5680-1937 Peter the Great St. Petersburg Polytechnic University, Saint Petersburg, Russian Federation Burlutskaya Zhanna 0000-0003-1106-5080 Peter the Great St. Petersburg Polytechnic University, Saint Petersburg, Russian Federation Zubkova Daria 0000-0002-2028-7251 Peter the Great St. Petersburg Polytechnic University, Saint Petersburg, Russian Federation Petryaeva Alexandra Complex Modelling of Regional Tourism Systems This study aimed to examine the prospects of various modelling tools in building complex models of regional tourism systems. It surveyed the international experience in forecasting tourist demands and modelling the tourism industry. It found that the hybrid approach – combining simulation modelling with econometric models to forecast tourist demands and deep learning models to process data from various sources – seems to be the most promising one. Simulation modelling is divided into two parts: system dynamics as a model of domestic tourism in terms of assessing state support’s impact on the development of tourist infrastructure and agent-based modelling, which is used to form tourists’ profiles and assess their needs as accurately as possible. Then, a more detailed study of the possibilities of using CGE models in the framework of integrated modelling of the tourism system, with an emphasis on sustainable development, was proposed. To reduce the level of uncertainty typical in a socio-economic system, integration into the CGE model of production functions was proposed. Thus, the potential applicability of using production functions for modelling tourism processes from the point of view of the state of the economy in a pandemic s being investigated. This study classified the production functions and adopted the function of constant elasticity of substitution to assess the income gained from the tourist products consumed by domestic tourists. Based on synthetic data, the possible income from tourist products were calculated using the income distribution in four groups of profitability. We performed the calculation using written code in the statistical programming language R. The formula we used considered the annual income of population groups, spending on rental housing and the consumer basket, as well as the elasticity of consumption of tourist services. 10.48554/SDEE.2023.3.5 519.876.5 simulation modelling domestic tourism modelling CGE model production functions CES function https://sustainable.spbstu.ru/article/2023.9.5/ 5.pdf