2782-6015 19 4 2026 1-213

RAR RUS 7-25 Kosolapova Natal'ia nakosolapova@sfedu.ru Khristova Sofia Industrial data: from a traditional asset to a key resource The relevance of the study is due to the growing interest of researchers and practitioners in the issue of attributing data to an asset, resource, and production factor. This trend is determined, on the one hand, by the increasing role of data for economic activity in general, and, on the other, by the gradual institutionalization of the term “data economy”. It should be noted that with significant variability of interpretations (as a new stage of economic development, as part of the digital transformation, as a management system), most researchers note a characteristic property: data is considered as a key asset and resource of the economy. Of particular interest is the use of data in industry in view of its large-scale digitalization and its system-forming role for the country’s economy, while the resource base is the basis for the functioning of enterprises. The purpose of the study is to determine how data as a resource is used in the company’s activities and what are the features of such a process, as well as to understand how industry representatives approach data in their activities in practice, to what extent data is a key resource, and what factors influence such correlation. The research methods include analysis and synthesis, systematic and comparative approaches, questioning the management level of industrial enterprises in the Rostov region, statistical (processing the results obtained) and econometric (building a binary logit model based on the questionnaire data) methods. The results of the study demonstrate that data in modern conditions is actually used in industrial enterprises as a resource, indirectly participating in the process of creating a product or service, enhancing the efficiency of using other resources. The specifics of industrial data as a resource, the effect of their use for the enterprise are revealed, the need for the formation of operational and strategic contours for the use of data as a resource in the activities of enterprises is determined. It is emphasized that the heads of industrial enterprises who participated in the survey are more likely to attribute data to a key resource if the degree of readiness of their enterprises to invest in data is high, as well as with the systematic use of data for managerial decision-making. The scientific novelty of the current study lies in the approach to data as a resource base for industry, with an emphasis on the direct involvement of data in the creation of products and services, as well as in the empirical assessment of industry representatives' opinions on evaluating data as a key resource of an industrial enterprise. The practical significance of the study is determined by the possibility of applying the conclusions obtained by the management of enterprises to revise approaches to data as an economic asset, to move from fragmentary data collection to their integrated use in production through the business processes of the enterprise and the formation of a strategy for their application in order to optimize production activities. The key conclusion of the study is that data is used as a resource in the activities of industrial enterprises, but their potential has not been fully exploited due to a lack of understanding in practice of the usefulness of data for production, the lack of a methodological basis for evaluating them and accounting for their contribution to the cost of enterprises, which is also reflected in the theoretical plan – the lack of an approach to data as a resource base for industry. In this regard, the areas of further research should cover the development of methodological aspects of data inclusion in the industrial resource base, the formation of a resource approach to data, the determination of the value and value of data, the development of data management systems in the enterprise, as well as the tightening of institutional mechanisms for regulating property rights and the creation of data markets. 10.18721/JE.19401 330.111.4: 004.6 data as a resource industrial data industrial resource base data properties industrial digitalization data economy digital economy digitalization https://economy.spbstu.ru/article/2026.120.1/ 01_kosolapova_hristova.pdf

RAR RUS 26-44 Polozhentseva Iuliia polojenceva84@mail.ru Bulatnikov Vladimir Managing an organization’s business processes based on a digital maturity assessment toolkit: a cluster-oriented approach The mere presence of information systems does not ensure higher manageability and productivity in organizations. Digital technologies become real tools for business process management only when they correspond to the current maturity level of the institution. The article presents a methodology for the cluster-based selection of innovative business process management tools in health care organizations based on the assessment of their digital maturity. The empirical basis consists of survey data from 390 medical workers. Using statistical analysis, a general factor of digital maturity was identified, which explains the evaluation of nine key business processes. Based on this general factor, a typology of six clusters was developed and grouped into three maturity zones: low, medium, and high. The low zone is characterized by a high share of routine operations, weak regulation, and the predominance of paper-based and manual practices. The medium zone reflects a transitional state. In this state, individual digital services are already used, but their connection with end-to-end pathways and management control remains insufficient. The high zone is associated with a more stable digital architecture, but may require further integration of data, standardization, and scaling of successful practices. The structure of digital transformation barriers changes qualitatively from resource constraints in low clusters to systemic integration problems in high clusters. On this basis, an integrated index of the digital maturity of a health care organization, a diagnostic scheme, and a rapid self-identification tool were developed. These elements make it possible to link the results of statistical typology with primary managerial diagnostics and to determine which tools should be applied in an organization based on its maturity level. Using the example of two health care organizations, the logic of targeted selection is demonstrated and the economic potential of reducing process losses is assessed. The calculations show that reducing routine workload can generate savings in working time, reduce errors, accelerate the patient pathway, decrease transaction losses, and increase the transparency of management control. The results indicate the need to align the choice of digital solutions with the maturity level of processes, the type of dominant barriers, and the organization’s readiness for the next stage of digitalization. This reduces the risk of implementing tools that exceed the organization’s actual digital capacity. The proposed methodology can be used for the typification of health care organizations and for targeted support of digitalization when implementing innovative business process management tools. 10.18721/JE.19402 338.24.004 business process management healthcare digital maturity cluster analysis cluster-based selection methodology medical organizations https://economy.spbstu.ru/article/2026.120.2/ 02_polozhentseva_bulatnikov.pdf

RAR RUS 45-65 Ali Amjad Zdol'nikova Svetlana s.v.muraveva@yandex.ru Assessment of the implementation of artificial intelligence technologies at an industrial enterprise in the context of Industry 5.0 (the case of Pakistani companies) It is considered that the degree of adoption of artificial intelligence (AI) technologies by manufacturing enterprises in emerging economies depends mainly on their internal capabilities and culture, while the surrounding ecosystem is considered only as a background, and not as a measurable factor. The authors’ research addresses this gap by developing and empirically testing a conceptual structural model based on nine hypotheses and eight constructs that links ecosystem networking, institutional and government support, digital infrastructure readiness, technological readiness, innovation culture, and dynamic opportunities with the introduction of AI and through it – with industrial innovation and competitiveness. The model combines the dynamic opportunity perspective, the institutional theory perspective, and the human-centered Industry 5.0 paradigm into a single ecosystem-level framework. At the same time, it is assumed that conditions at the ecosystem and infrastructure level form the internal readiness of the enterprise, which, in turn, encourages the introduction of AI and subsequent productivity. Primary survey data was collected from 182 managers from five manufacturing subsectors in Pakistan. Four of the nine hypotheses were confirmed: ecosystem connections were associated with technological readiness, digital infrastructure was associated with dynamic capabilities, institutional support was associated with an innovative culture, and the introduction of AI was closely related to indicators of competitiveness. Technological readiness and innovation culture did not demonstrate a reliable unique influence on decision-making, hypothetical deterrence from institutional support was not detected, and the two constructs – ecosystem connections and dynamic capabilities – were too correlated to be tested as independent predictors. The study provides one of the first tests of ecosystem and institutional prerequisites for assessing the implementation of AI using the example of South Asian industry at the enterprise level, reports on the limitations of measurement and allows formulating recommendations for managers in the field of industrial policy based on AI. Future research will focus on forming yet untested hypotheses using refined, abbreviated data to establish the direction of causal relationships between ecosystem conditions, AI adoption, and enterprise performance. 10.18721/JE.19403 338,45:004.8(549.1) AI adoption Industry 5.0 Pakistani industrial enterprises dynamic capabilities struc-tural equation modeling https://economy.spbstu.ru/article/2026.120.3/ 03_ali_zdolnikova.pdf

RAR RUS 66-83 Palash Svetlana svpalash@yandex.ru Palash Marina State industrial policy and development institutions: elements of assessment of systemic interrelations The relevance of this research topic is due to the importance of analyzing the systemic relations of state development institutions for assessing their effectiveness and identifying problems in implementing state industrial policy related to systemic relations and interactions. The objective of this study is to develop a methodological tool for assessing the systemic relations of the Industrial Development Fund (IDF) as a state institution for industrial development implementing state industrial policy. The research methods utilize system and economic analyses. A distinctive feature of the developed tool is its consideration of the nature of the IDF’s interactions with government bodies, other state development institutions, and industrial enterprises, as well as the influence of the external environment on these interactions, including macroeconomic conditions and the state and dynamics of the industrial complex. To assess the systemic interrelations of the IDF, the authors develop four groups of indicators characterizing: 1) the volume of financial support for industrial enterprises through the instruments of the IDF; 2) securing the IDF’s obligations and relationships with other state development institutions; 3) the state and dynamics of the manufacturing complex; 4) the influence of the external environment and macroeconomic conditions (indicators characterizing the dynamics of the Bank of Russia key rate) on these interactions. The study shows that for the period under review (from 2020 to 2024), the years with a significant increase in production and investment in fixed assets of manufacturing enterprises (2021, 2023, 2024) are characterized by an increase in the Bank of Russia key rate, as well as a decrease in the net provision of loans by the IDF to industrial enterprises (activities with targeted funds). An increase in the Bank of Russia key rate means an increase in the cost of commercial lending, including for industrial enterprises. The identified interrelations reflect the interaction of the mechanisms of state industrial and monetary policy. Changes are also occurring in the structure of the IDF’s loan repayment security for various forms: the share of collateral and surety is decreasing, the share of bank guarantees, which become the primary form of collateral at the end of the period under review, is increasing, and the share of other collateral is also increasing. The identified structural changes reflect changes in the intensity of the IDF’s interactions with other state development institutions and credit organizations. The scope of application of the obtained results includes state industrial policy and the activities of state industrial development institutions in supporting industrial enterprises. 10.18721/JE.19404 338.2 industry industrial development state industrial policy state development institutions systemic relationships methodological assessment tools https://economy.spbstu.ru/article/2026.120.4/ 04_palash_palash.pdf

RAR RUS 84-101 Mihailova Anna Creative sector as a source of small spatial effects: a methodological approach for a resource-based microregion  Creative industries are increasingly becoming involved in regional entrepreneurial and spatial development, gradually moving beyond the cultural sphere. Their influence is reflected not only in the creation of cultural products and new forms of employment, but also in the development of small and medium-sized enterprises, tourism, digital services, and local markets. This increases the need for a methodological approach that can assess both the scale of the creative sector and the additional socio-economic effects it generates in remote regions with a predominantly resource- based specialization. The aim of the article is to substantiate and test a methodological approach to assessing the potential of the creative sector and its associated entrepreneurial and tourism effects, taking into account digital, social and labor, and institutional conditions. The empirical base is a balanced panel of 11 regions of the Far Eastern Federal District covering 2019–2025. The research object is the creative sector of the Far Eastern regions, interpreted as an element of the macroregion’s spatial development system. The year 2019, the last pre-pandemic year, is used as the base year for index calculations; this ensures the comparability of time series and makes it possible to account for the changes that occurred in regional economies in 2020–2025. The data are drawn from official statistics and the Unified Register of Small and Medium-Sized Enterprises. Methodologically, the study is based on a “resource – channel – effect” framework involving a step-by-step analysis of the creative sector’s initial resources, the mechanisms of their economic realization and the resulting socio-economic outcomes. The toolkit includes the normalization of indicators grouped into five blocks – resource, digital, market, social and labor, and institutional – as well as a set of econometric procedures. The main stages are the preparation and normalization of the initial dataset, construction of an integral creative-sector potential index, estimation of panel models with fixed effects and robustness testing. The proposed approach differs from conventional methods focused mainly on the direct contribution of creative industries to gross regional product (GRP) by emphasizing the accompanying effects of their development. The calculations indicate a statistically robust positive association between the share of creative-economy gross value added in GRP and indicators of small and medium-sized enterprise development and tourist flows. The integral index provides a more detailed picture of interregional differences in creative-sector development. The proposed methodological framework can support public authorities in designing measures for creative-industry development, setting regional priorities, and monitoring and evaluating regional creative-sector programs. 10.18721/JE.19405 332.14+338.48+004.8 creative sector small spatial effects Russian Far East panel data creative-sector potential index regional policy https://economy.spbstu.ru/article/2026.120.5/ 05_mihaylova_a_v_.pdf

RAR RUS 102-113 Mwamba Martin Interregional cooperation as a tool for reducing spatial differentiation: governance mechanisms and success factors This article examines interregional cooperation as a strategic instrument for reducing spatial differentiation in the Russian Federation. The relevance of the study is due to the persistence of significant regional disparities despite the prolonged use of equalization policies, highlighting the need for mechanisms that move beyond redistributive approaches toward coordinated development. The aim of the study is to identify governance mechanisms of vertical and horizontal cooperation and determine the factors that ensure their effectiveness in reducing spatial inequality. The central hypothesis is that the success of interregional initiatives depends on the presence of structured governance mechanisms capable of ensuring institutional synergy and overcoming administrative fragmentation. The research is based on a qualitative case study methodology. Four successful interregional projects are analyzed: the West Siberian Interregional Research and Education Center, the Oil and Gas Cluster of Tyumen Oblast, the Interregional Cluster for Nuclear Power Engineering, and subcontracting projects between the Chambers of Commerce and Industry of Arkhangelsk and Yaroslavl Oblasts. The empirical base includes official documents, analytical reports, expert assessments, and open-source materials. The results identify three key models of interregional cooperation: institutional, coordination, and network-based. The findings demonstrate that the most sustainable outcomes emerge from hybrid configurations combining vertical support (federal, institutional recognition, regulatory backing) with horizontal interaction (regional collaboration, business participation, and knowledge exchange). Key success factors include political commitment of regional leadership, reliance on established economic specialization, active involvement of private sector actors, the presence of dedicated project management structures, diversified financing mechanisms, and a results-oriented project approach. The scientific novelty lies in the systematization of governance models of regional cooperation and the empirical identification of success factors within the Russian spatial development context. The practical significance lies in the applicability of these findings for designing interregional initiatives and improving public policy instruments. The study concludes that interregional cooperation is an effective mechanism for reducing spatial differentiation when supported by institutional formalization, diversified, and coordinated stakeholder engagement. The greatest potential is observed in sectors critical to technological sovereignty, including the fuel and energy complex, nuclear power engineering, science and education. The study is limited by its focus on successful cases. Future research should examine unsuccessful projects, assess long-term impacts on regional inequality, develop quantitative evaluation tools, and explore the role of digital platforms in scaling cooperative models. 10.18721/JE.19406 338.24.004 interregional cooperation spatial differentiation governance mechanisms industrial clusters regional development vertical integration horizontal integration economic geography https://economy.spbstu.ru/article/2026.120.6/ 06_mvamba.pdf

RAR RUS 114-136 Q-4229-2017 57195759467 0000-0003-3644-4239 Voronezh State Technical University Shkarupeta Elena 9056591561@mail.ru

20 letiya Oktyabrya st., 84, Voronezh, Russia

57190260598 0000-0001-6888-1981 V.I. Vernadsky Crimean Federal University Kirilchuk Svetlana skir12@yandex.ru

Prospekt Vernadskogo 4 , Simferopol, Republic of Crimea, 295007

Nalivaychenko Ekaterina Mikhailov Pavel Innovative development of high-tech industry and assessment of the digital maturity of economic systems The article is devoted to the issues of innovative development of high-tech industry and assessment of digital maturity of economic systems. The aim of the research is to develop theoretical and applied approaches to assessing the effectiveness of high-tech industry based on the methods of innovation economics and machine learning (ML) in the context of analyzing and increasing the digital maturity of enterprises and ecosystems. Methods of system analysis, economic and statistical analysis (including analysis of GRP dynamics, labor productivity and innovation activity), methods for evaluating the effectiveness of digital assets (LTV, CAC), as well as structural modeling of business processes were used. The article examines the evolution of approaches to innovation management in industry using the example of the Republic of Crimea. In the first part of the work, an analysis of the current state of the region’s high-tech sector was carried out using data economy metrics, and a gap in the level of digital maturity between Crimean enterprises and all-Russian leaders was revealed. The second part of the study examines the architectures of predictive pricing systems and models of decentralized interaction (Web3). It has been established that the key barrier remains the low level of gross value added in knowledge-intensive industries, while investments in fixed assets are growing. It is shown that the targeted implementation of ML algorithms in inventory and logistics management can increase operational efficiency by 12–15% without significant capital costs. A modified balanced scorecard (Digital BSC) has been developed and substantiated, adapted to assess the digital maturity of industrial enterprises in the region. A methodology for assessing the digital maturity of an ecosystem is proposed, taking into account coevolutionary processes. The proposed Digital BSC system, which includes, along with financial results, Data Quality Index and staff innovation sensitivity metrics, makes it possible to quantify the level of digital maturity and identify “bottlenecks” in data management. The necessity of the transition from extensive digitalization to the purposeful development of competencies in the field of Data Science and industrial design as a basis for increasing the digital maturity of ecosystems is substantiated. For the Crimean industry, a decomposition of innovation processes was carried out at the level of “data → forecast → solution”, imbalances in the structure of investment in R&D were identified, and a mechanism for the “digital twin” of the regional industrial complex was proposed for testing government support measures. 10.18721/JE.19407 658 economics of innovation industry machine learning artificial intelligence digital trans-formation digital maturity data economics Web3 https://economy.spbstu.ru/article/2026.120.7/ 07_shkarupeta_kirilchuk_nalivaychenko_mihaylov.pdf

RAR RUS 137-156 Lyukevich Igor Vega Bonilla Gerald Samuel Melikyan Artsrun Success factors and scaling constraints of institutional innovations  Countries are diversifying their payments, and this is a global trend. This article examines (as an institutional innovation project) a unique mechanism that enables participants in foreign economic activity to make payments in their national currencies – Sistema de Pagos en Monedas Locales (SML) – in South American countries. Unlike technological innovations (blockchain, smart contracts), the SML institutional innovation focuses on restructuring the rules of interaction between economic agents, reducing transaction costs, and creating an alternative institutional environment for foreign trade operations. The aim of the study is to identify success factors, assess the contribution to business competitiveness, and the limitations of scaling this institutional innovation project using the example of cross-border SML. This approach aims to formulate universal lessons and develop a methodology for creating similar systems. Based on an analysis of the system’s evolution (2008–2026), its operational mechanism, and statistical data, it was established that the SML reduces transaction costs for small and medium-sized enterprises (SMEs) by 15–20%, performs a countercyclical function during periods of currency crises, and serves as an alternative channel for imports in conditions of dollar liquidity shortages. However, the system’s scalability is constrained by a number of limitations: the lack of mechanisms for hedging currency risks and lending, the lack of operational continuity (the system does not function on holidays and weekends), the persistence of structural asymmetries (more than 99% of transactions are accounted for by Brazilian exports to Argentina), and the final dollar clearing between central banks. The following success factors have been systematized: voluntary participation, focus on SMEs as “early adopters”, a simple and understandable settlement cycle (D+0, D+1, D+2), and institutional support from central banks and governments. A roadmap for the creation and scaling of institutional innovation projects has been developed, comprising four stages (inception, development, maturity, and expansion) across four areas (financial mechanism, technological platform, institutions and law, clients and adoption). The results are applicable to the design of similar systems, for example, within the EAEU or BRICS. 10.18721/JE.19408 001.895:336.7 institutional innovation innovation ecosystem cross-border innovation innovative payment mechanisms innovation diffusion innovation success factors innovation scaling constraints innovation adoption SML MERCOSUR international settlements https://economy.spbstu.ru/article/2026.120.8/ 08_lyukevich_bega_bonilla_melikyan.pdf

REV RUS 157-179 Polyakov Ruslan Analysis of research on self-organization of economic clusters based on a bibliometric review Increased international competition under conditions of chronic turbulence in the global economic system shifts the focus of modern research towards regionalization and the determinants of spatial concentration of economic activity. However, despite the significant amount of knowledge accumulated in the world, the phenomenon of self-organization of industrial clusters has not yet received sufficient theoretical understanding. The methodological complexity of its study gives rise to a conceptual gap between empirical data and existing models. Therefore, the aim of the study is to synthesize the results of a systematic review of the academic literature for 1980–2021 on methods and approaches to the analysis of industrial clusters with a focus on identifying studies in the field of their spatial self-organization. The presented study tests the hypothesis that clusters have properties of a self-organizing dynamic system that are fundamentally different from the prerequisites and mechanisms inherent in traditional theoretical models. The implicit nature of these processes is that the endogenous forces of spatial concentration, specialization and cooperation give rise to a spontaneous order that cannot be adequately described within the framework of dominant managerial or neoclassical approaches that emphasize externalities of scale or targeted strategic regulation. To this end, the paper applies multivariate bibliometric analysis to the 2000 most cited documents in the Scopus database from 1980 to 2021, including keyword frequency analysis, citation mapping, topic evolution, Bradford’s law, and the PRISMA flowchart for systematic review of publications. The study revealed that the fundamental issues of self-organization of clusters remain poorly understood and ignored in academic circles, and Russian research mainly follows the principles of Porter management school, which limits the development of cluster structures in the Russian Federation. The work constructed thematic maps and networks of keywords that confirm the direct connection of self-organization with agglomeration, concentration, and local production systems. The theoretical significance of the presented research lies in substantiating the need for a transition from “Porterianism” to the theory of a self-organizing cluster, and the practical significance is in systematizing methods for identification that contribute to the improvement of regional policy and cluster management strategies. 10.18721/JE.19409 332.1 bibliometric analysis industrial cluster self-organization new economic geography spa- tial concentration Porterianism cluster identification methodology https://economy.spbstu.ru/article/2026.120.9/ 09_polyakov.pdf

RAR RUS 180-197 Flek Mikhail rostvertol@aaanet.ru Ugnich Ekaterina ugnich77@mail.ru Human capital reproduction of an industrial enterprise in the context of the distribution of artificial intelligence technologies  The relevance of this study is determined by the need to improve human capital manage- ment systems at enterprises in the context of the introduction of new technologies transforming production and business processes. For large companies with sufficient resources, one solution to this problem may be the creation of a human capital reproduction ecosystem in which the enterprise acts not only as the end consumer but also as a customer and co-producer of personnel. This paper examines the development of such an ecosystem in the context of the spread of artificial intelligence (AI) technologies. The aim of the study is to identify the characteristics of human capital reproduction in an enterprise amid the spread of AI technologies based on employee assessments of their applicability, loyalty, and satisfaction. The scientific novelty lies in the development of a methodological approach to assessing the reproduction of human capital in an industrial enterprise amid the spread of AI technologies, based on the perception of these technologies by those who hold human capital. The theoretical basis consists of the works of Russian and international authors devoted to the reproduction and management of human capital, as well as the development of an ecosystem approach in the social and labor sphere. The use of the index method allowed us to obtain assessments reflecting the attitudes of employees and students toward AI technologies. The empirical base was formed by the results of a survey among employees of the mechanical engineering company that initiated the ecosystem, and students of the university included in this ecosystem. A total of 72 employees and 47 students were surveyed. The results yielded assessments of employee and student loyalty and satisfaction with AI technologies, providing insight into the transformation of various stages of human capital reproduction in the context of the introduction of new technologies. Overall, human capital holders positively evaluate the use of AI technologies; however, the loyalty index of both employees and students revealed that absolute adherents of these technologies are in the minority. Employee satisfaction is rated low (47.92), while that of students is average (76.45). This is due to the fact that the use of AI in the educational process, which underlies the stage of human capital formation, is significantly more intensive. Based on the data obtained, key areas of transformation in the human capital reproduction ecosystem in the context of the spread of AI technologies are identified. 10.18721/JE.19410 331.108 human capital human capital reproduction ecosystem human capital management artificial intelligence technologies industrial enterprise https://economy.spbstu.ru/article/2026.120.10/ 10_flek_ugnich.pdf

RAR RUS 198-213 Antonov Aleksandr Ilyin Igor ilyin@fem.spbstu.ru Levina Anastasia alyovina@gmail.com Self-learning agent model for adaptive planning of multimodal transportation  Multimodal transportation is characterized by high level of uncertainty, heterogeneity of participants (rail, maritime, road transport), and technological constraints, which make traditional centralized planning methods based on static optimization models insufficiently effective. A contradiction arises between need for global coordination of supply chains and inability to promptly adapt to dynamic changes in environment without loss of flexibility. Additional complexity comes from need to coordinate decisions among independent participants of transport process, each having own objectives and constraints. The aim of the article is to develop a self-learning multi-agent model for adaptive planning of multimodal transportation based on decentralized decision-making and parametric adaptation of agent criteria. Methodological basis combines principles of agent-based modeling, elements of decision theory, and formalization of participant behavior through universal satisfaction function reflecting multi-criteria nature of transport processes. Within study, analysis of existing approaches to multimodal transportation planning, formalization of requirements for mathematical methods, and design of agent structure representing key elements of transport system and their interaction were carried out. As a result, mathematical model is proposed in which each element of transport network is represented as autonomous agent with own criteria (cost, time, resources) and local decision-making mechanism. Interaction of agents is implemented through coordination mechanism that ensures formation of consistent transportation plan without centralized control. Key element is self-learning mechanism: system adapts priorities of agents by comparing expected and actual outcomes of operations, accumulating experience to improve accuracy of subsequent decisions and robustness to external disturbances. Novelty lies in development of formalized model of self-learning multi-agent system that enables adaptation of decision-making parameters based on retrospective analysis and allows consideration of recurring patterns. Practical significance is confirmed by possibility of using developed model in intelligent logistics platforms, as well as by reducing need for complete re-planning when deviations occur and by increasing robustness of transport processes. The results demonstrate potential of multi-agent approach for efficient management of multimodal transportation under conditions of high uncertainty. 10.18721/JE.19411 330.46 multimodal transportation multi-agent systems adaptive planning agent satisfaction functions self-learning systems distributed decision-making logistics systems transport management systems https://economy.spbstu.ru/article/2026.120.11/ 11_antonov_ilin_lyovina.pdf