2024. No. 4 Vol.18

      The supply chain management’s effectiveness depends, among other things, on the selection and coordinated interaction with product consumers. This article is devoted to the development of a method for selecting a consumer in the regional wholesale and retail fuel market. The methodological basis of the study is the theory of statistical analysis and neural networks. The main tool for developing the methodology was neural network technologies, with the help of which it is most likely possible to correctly estimate the boundaries for indicators’ values that characterize consumers and reflect their history of purchasing behavior, to select potential clients and the possibility of further cooperation with existing ones. The information base for the work is the data on consumers of a given company’s products, data from the 2GIS electronic directory, as well as the results of the primary statistical analysis and forecasts made based on neural networks of various topologies. The author presents his methodology for selecting a consumer. It has the potential for development and implementation for solving a number of other management problems. As part of the testing, the best configuration (topology) of the neural network was determined, and standard values of entry barriers when consumer choice accomplished were assessed. The methodology we developed was tested using the example of a company operating in the wholesale and retail fuel market in Novosibirsk and the Novosibirsk region. When verifying the neural network model, the quality of client classification was compared based on logistic regression, decision tree and random forest models and we found that the neural network approach provides the best results for assessing the degree of client suitability. As a result of testing the methodology, recommendations for improving neural network models were developed, including expanding the set of factors that determine the characteristics of consumers, as well as optimizing the internal structure of neural networks.

      Management of strategic development of Russian regions is a complex task, the solution of which is associated with a set of difficulties of methodological nature. In particular, there is a low quality of formed forecast assessments on the main parameters under consideration. Despite the availability of research in this area and regulatory legal framework, strategic planning documents in Russia are often not linked to each other, are repeatedly revised in the course of implementation and, ultimately, are not fully implemented. This is largely due to the fact that the available scientific potential is not fully utilized, including the development of relevant information systems. The aim of this research is to develop a decision support toolkit for strategic planning of regional development. Agent-based modeling, adaptive management, data mining and scenario modeling are used as the main research methods. In the course of the research, the concept of toolkit formation is proposed based on the construction of an intelligent adaptive simulation model (IASM), taking into account the theory of strategic planning and the ability to process heterogeneous data. The proposed structure of IASM includes four interrelated hierarchical levels – intelligent agents, macro-processes, management system and external environment. Special attention is paid to the development of a model of adaptive behavior of an intelligent agent. The proposed approach to implementation will make it possible to cover the whole range of tasks – from the analysis of input data to the development of management decisions. The software implementation of the model thus developed is carried out using the AnyLogic toolkit. 

The article was prepared with the financial support of the Russian Science Foundation, project No. 23-28-00871.

      In this paper, we present a method of forming norms for evaluating the results of the functioning of complex systems applicable to socio-ecological and economic systems, taking into account the priorities of the development of the regions of the Russian Federation. The methodology involves the selection of normative values from a set of norms based on two methods: the first is based on the construction of econometric models using statistical data for a set of subjects (the first type) and for one selected subject (the second type). The second method uses the methodology of Bayesian intelligent measurements based on the regularizing Bayesian approach (the third and fourth types). Depending on the result of the calculations, a norm is selected that gives a higher (in the case of high priority), average (in the case of medium priority) and lower (in the case of low priority) normative value of the evaluated effective features characterizing the development of the subject. The implementation of the method is demonstrated by the example of the regions of the Central Federal District, including the Tula Region, for which econometric and fuzzy models of the relationship between the volume of gross regional product with the value of fixed assets and the number of employees for sections A (Agriculture, forestry, hunting, fishing and fish farming) and C (Mining) according to OKVED1 are constructed, forming the raw materials sector according to data for 2007–2022. The EFRA and Infoanalyst 2.0 software platforms are used as tools. The results obtained can be used by regional authorities in the formation of norms to assess the results of the functioning of the regions in the short and medium term. 

The study was carried out at the expense of a grant from the Russian science Foundation № 24-28-20020 and Tula Region.

      Currently, many companies engaged in the production of medium-term turnover goods, are faced with the need to create a high-level design of a software complex that allows them to support a full cycle of sales planning, production, logistics and marketing campaigns. This is due to the economic development of the enterprise and the integration of independent software systems/modules that allow for the implementation of limited business processes without connection with related functions and business processes of the enterprise. Thus, enterprises find themselves in a situation where various departments have implemented a disparate set of information systems and software modules within which local accounting and analytics of various operations are carried out, while the software and analytical complex as a whole does not provide a complete, connected and cyclical planning process. This paper presents a model of requirements for functions, information objects and data flows, providing end-to-end planning, as well as an approach to identify missing objects of the existing information complex of the enterprise. An analytical network consisting of missing elements has been developed, taking into account the dependencies and interrelationships of information objects and software modules, which makes it possible to form a priority vector of the relative importance of software components. This vector represents a set of priorities for improvements to the enterprise software package and allows you to more effectively allocate the resources of the development team for the software implementation of missing functions, information objects and integration data flows between software modules.

      The rapid digital transformation of the real estate brokerage industry in China has revolutionized traditional business models, with Lianjia (Beike) at the forefront of this shift. This study explores Lianjia’s journey from a conventional brokerage firm to a leading digital platform, analyzing the strategic digitalization of housing data through the creation of the Housing Dictionary, the development of the agent cooperation network (ACN), and the implementation of a management information systems (MIS) based Offline-to-Online (O2O) business model. Through a qualitative case study methodology, this research highlights how Lianjia’s innovative use of technology has enhanced operational efficiency, customer satisfaction and competitive advantage. The findings provide valuable insights into the potential of digital platforms to drive continuous innovation and transformation in the real estate industry. This study also discusses the broader implications for the digital economy and offers recommendations for businesses aiming to undergo similar transformations.

      This paper considers a mathematical model that allows managers of a timber enterprise to develop supply chains and manage the pricing policy of the organization. This model is a modification of the model developed earlier and differs from it by taking into account the technology of raw material cutting. The model takes into account the consumption rates of raw materials, purchases on the commodity exchange, transportation of products and pricing policy of the enterprise taking into account the demand. The purpose of the model is to maximize the value of operating profit of the enterprise. When searching for a solution, an optimization strategy is applied which includes two stages: application of linear optimization at the first stage and genetic algorithm at the second stage. As a result of testing the model at one of the timber processing enterprises in the Primorsky Territory, data were obtained, based on which recommendations are formulated for managers of the company regarding cooperation with loggers. This work represents an important step in the development of supply chain management methodology in the timber industry, taking into account the technology of raw material cutting. Further research may include modification of the model using stochastic factors, improving decision-making methods and development of more accurate product demand functions. The work has practical significance for enterprises of the timber processing industry, since it can contribute to the improvement of their production processes and increase profits.