Determining the development model of the transport and logistics system of a smart city

   Relevance. Today there is a tendency for many industrial enterprises to switch from rail to the use of road transport, which significantly increases the load on the urban transport network and affects its quality. Population growth, exacerbating problems in the field of traffic organization negatively affect the time of movement and costs for business, population and the state. In this situation, both models are needed to predict losses for each participant in the city's streaming processes, as well as the selection of signs that can be influenced by the municipality, stakeholders and the population. The development of these models opens up great prospects for use in the field of urban planning, the economic justification of the proposed activities and investment projects, as well as in the field of ensuring the growth of the quality of human life.

   The purpose is to train models and achieve the best indicator of the quality of loss forecasting for participants in transport processes in the city.

   Objectives: to select the most relevant features of assessing smart cities in the world from the standpoint of mobility, sustainable development and the introduction of information and communication technologies; Select the best forecasting models make a forecast of temporary and monetary losses for cities of different populations; propose a new vision for infrastructure development and shape models for reducing peak congestion in the city.

   The methodology is prediction using machine learning techniques.

   Results. The best model to predict congestion is linear regression. When predicting losses ‒ LightGBM model.

   Conclusions. The use of machine learning and the proposed "smart road" makes it possible to highlight development models that reduce peak congestion in the transport and logistics system of a smart city.

1. Shulzhenko T.G., Zhuk A.E. A value-oriented approach to assessing the quality of services in the logistics system of public passenger transport. Teleskop : zhurnal sociologicheskih i marketingovyh issledovanij = Telescope : Journal of Sociological and Marketing Research. 2021;(2):100-109. (In Russ.)

2. Bochkarev A.A., Soloviev D.S. The problem of optimizing the network structure of supply chains and methods of solving it. Ekonomika: vchera, segodnya, zavtra = Economy: Yesterday, Today, Tomorrow. 2024;14(5-1):502-511. (In Russ.)

3. Silkina G.Yu., Shevchenko S.Yu., Shcherbakov V.V. Consumer value of artificial intelligence technologies in digital logistics and supply chain management. In: Intellektual'naya inzhenernaya ekonomika i Industriya 5.0 (INPROM-2024) : sbornik trudov X Mezhdunarodnoi nauchno-prakticheskoi konferentsii = Intelligent Engineering Economy and Industry 5.0 (INPROM-2024) : Collection of works of the X International Scientific and Practical Conference. St. Petersburg: POLITEKh-PRESS; 2024. P. 243-247. (In Russ.)

4. Gdalin A.D. Trends in population mobility research ‒ a component of spatial behavior in an urban environment. Regional'nye geosistemy = Regional Geosystems. 2024;48(3):354-367. (In Russ.)

5. Labajo V., Nagel S. Delivering seamless urban mobility: expert recommendations and best practices for consumer-centric Mobility-as-a-Service solutions. Urban, Planning and Transport Research. 2025;13(1). doi: 10.1080/21650020.2025.2501999

6. Makarevich S, Yanishevsky O. Optimizing urban mobility: the potential and limitations of the mobility-as-a-service model. Gorodskie issledovaniya i praktiki = Urban Research and Practice. 2024;9(3):78-94 (In Russ.)

7. Vasiliev V.P. Urban mobility trends. Avtomobil'nye dorogi = Highways. 2024;(2):76-77. (In Russ.)

8. Tasueva T.S., Borisova V.V. Institutional framework of the digital infrastructure of the region. Moscow: IP Aborkina Ekaterina Oskarovna; 2022. 213 p. (In Russ.)

9. Kulyev S. Smart transport systems: how technologies are changing urban mobility. Vestnik nauki = Bulletin of Science. 2024;1(11):920-923. (In Russ.)

10. Afanasenko I.D., Borisova V.V. Digital technologies in the circular value chain. In: Transformatsiya ekonomiki evraziiskikh stran v usloviyakh neopredelennosti : sbornik nauchnykh statei = Transformation of the economies of Eurasian countries in conditions of uncertainty : Collection of scientific articles. St. Petersburg: Izdatel'stvo Sankt-Peterburgskogo gosudarstvennogo ekonomicheskogo universiteta; 2024. P. 109-113. (In Russ.)

11. Cannon R., Mukhtar-Landgren D., Fred M. Organising integrated urban mobility: actions, roles and identities in an evolving landscape. Mobilities. 2025. P. 1-19. doi: 10.1080/17450101.2025.2484233

12. Galanakis K., Heinz H., Marggraf C. Place-based sustainable urban mobility: a conceptual framework to spark local designs. Regional Studies. 2024;(58):2419-2434. doi: 10.1080/00343404.2024.2406290

13. Gergis F. H. Collaborative forms of governance in sustainable urban mobility schemes at the sub-governmental levels: a scoping literature review. International Journal of Urban Sustainable Development. 2024;(16):343-359. doi: 10.1080/19463138.2024. 2411049

14. Shaitura S.V., Kozhaev Yu.P. Transport ecosystems. Slavyanskij forum = Slavic Forum. 2023;(2):226-233. (In Russ.)

15. Shulzhenko T.G., Zhuk A., Ivanova D.P. Logistics of new urban mobility: a value-oriented approach : monograph. Moscow: Nauchno-izdatel'skii tsentr INFRA ‒ M; 2023. 546 p. (In Russ.)

16. Eldarkhanov H.-M.Yu., Abubakarov M.V. Crisis of urban transport production: scientific problems and current solutions. Makhachkala: Alef; 2021. 96 p. (In Russ.)