Introduction. The relevance of the study is driven by the challenges and threats to transport facilities and infrastructure, as well as the opportunities for digital transformation of the operational and service activities of the Russian Ministry of Internal Affairs. The increase in unauthorized interference and the public danger of encroachments necessitate the optimization of transport police operations, which can be effectively achieved using artificial intelligence methods, specifically neural network forecasting. The aim is to systematize the theory and methodology of applying neural network technologies to forecast offenses and crimes at transport infrastructure facilities, in order to enhance the efficiency of transport police. Research methods: general scientific methods of analysis, systematization, and concretization, applied to information on the use of artificial intelligence and neural network methods for forecasting transport offenses and crimes. Results. Domestic and foreign AI technologies used in forecasting offenses and crimes were analyzed; neural network forecasting methods suitable for modeling offenses and crimes were systematized; an algorithm for forecasting offenses and crimes in transport and at transport infrastructure facilities using neural network AI technology was specified. It is shown that Multilayer Perceptron (MLP), Recurrent Neural Network (RNN), Temporal Convolutional Network (TCN), and Graph Neural Network (GNN) can be applied for both operational (real-time) and strategic (criminological) forecasting. Examples of neural network models for these tasks are provided. Based on the analysis, an algorithm for developing a neural network forecasting model is formulated, describing its four implementation stages to enable practical model development.
crime intelligence forecasting, artificial neural network, neural network crime prediction, neural network offense analysis, intelligent crime prediction, criminological forecasting, IT for offense prediction
1. Zahvatov, I. Yu. Prognozirovanie kak element informacionno-analiticheskogo obespecheniya deyatel'nosti organov vnutrennih del / I. Yu. Zahvatov, M. N. Pcholovskiy // Vysshaya shkola: nauchnye issledovaniya : materialy Mezhvuzovskogo mezhdunarodnogo kongressa, Moskva, 24 iyunya 2021 goda. – Moskva: Infiniti, 2021. – S. 14-24.
2. Kaybichev, I. A., Kaybicheva, E. I. Matematicheskoe modelirovanie vremennogo ryada kolichestva prestupleniy v Rossii //Vestnik ekonomiki, upravleniya i prava. – 2019. – №. 4 (49). – S. 80-85.
3. Kiselev, A. A. Sezonnost' prestupnosti kak ob'ekt kriminologicheskogo izucheniya / A. A. Kiselev // Pravovaya kul'tura. – 2020. – № 2(41). – S. 139-150.
4. Kleymenov, M. P. Ugolovno-pravovoe prognozirovanie / M. P. Kleymenov. – Tomsk : Nacional'nyy issledovatel'skiy Tomskiy gosudarstvennyy universitet, 1991. – 167 s.
5. Petrova, V. Yu. Rol' prognoziruyuschih modeley v upravlenii organami vnutrennih del (na primere prestupleniy, svyazannyh s legalizaciey prestupnyh dohodov) / V. Yu. Petrova // Vestnik Vladimirskogo yuridicheskogo instituta. – 2013. – № 2(27). – S. 107-109.
6. Simonova, E. N. Realizaciya logisticheskoy regressii v R, kak naimen'shey vozmozhnoy neyronnoy seti / E. N. Simonova // Modern Science. – 2021. – № 1-1. – S. 491-495.
7. Suhodolov A. P., Bychkova A. M. Iskusstvennyy intellekt v protivodeystvii prestupnosti, ee prognozirovanii, preduprezhdenii i evolyucii //Vserossiyskiy kriminologicheskiy zhurnal. – 2018. – T. 12. – №. 6. – S. 753-766.
8. Ul'yanov A. D., Vlasov B. E. Teoretiko-metodologicheskoe obespechenie analiticheskoy raboty v organah vnutrennih del v sovremennyh usloviyah //Trudy Akademii upravleniya MVD Rossii. – 2023. – №. 1 (65). – S. 24-31
9. Fedorova O. B., Heylo L. G. Statisticheskie metody analiza, ocenki i prognozirovaniya operativnoy obstanovki: uchebno-metodicheskoe posobie dlya sotrudnikov shtabnyh podrazdeleniy organov vnutrennih del //M.: OAD MVD Rossii. – 2018
10. Shalagin A. E., Sharapova A. D. Kriminologicheskoe prognozirovanie i planirovanie v deyatel'nosti organov vnutrennih del //Vestnik ekonomiki, prava i sociologii. – 2017. – №. 2. – S. 127-130
11. Alsubayhin A., Ramzan M. S., Alzahrani B. Crime Prediction Model using Three Classification Techniques: Random Forest, Logistic Regression, and LightGBM //International Journal of Advanced Computer Science & Applications. – 2024. – T. 15. – №.
12. Ansfield, B. The broken windows of the Bronx: Putting the theory in its place //American Quarterly. – 2020. – T. 72. – №. 1. – S. 103-127.
13. Bifari, E. et al. Text mining and machine learning for crime classification: using unstructured narrative court documents in police academic //Cogent Engineering. – 2024. – T. 11. – №. 1. – S. 2359850.
14. Clavell, G. G. (2018). Exploring the ethical, organizational and technological challenges of crime mapping: A critical approach to urban safety technologies. Ethics and Information Technology, 20(4), 265–277. https://doi.org/https://doi.org/10.1007/s10676-018-9477.
15. Dakalbab, F. et al. Artificial intelligence & crime prediction: A systematic literature review //Social Sciences & Humanities Open. – 2022. – T. 6. – №. 1. – S. 100342.
16. Johnson, T. L. et al. Police facial recognition applications and violent crime control in US cities //Cities. – 2024. – T. 155. – S. 105472.
17. Kim, G. et al. Crime Mapping in Urban Environments Using Explainable AI: A Case Study of Daegu, Korea //Sustainable Cities and Society. – 2025. – S. 106507.
18. Lee, W. D. et al. The influence of intra-daily activities and settings upon weekday violent crime in public spaces in Manchester, UK //European Journal on Criminal Policy and Research. – 2021. – T. 27. – №. 3. – S. 375-395
19. Marciniak, D. Algorithmic policing: An exploratory study of the algorithmically mediated construction of individual risk in a UK police force //Policing and society. – 2023. – T. 33. – №. 4. – S. 449-463.
20. Massarelli, C., Uricchio, V. F. The contribution of open-source software in identifying environmental crimes caused by illicit waste management in urban areas //Urban Science. – 2024. – T. 8. – №. 1. – S. 21.
21. Mishra, R. K. et al. Analysis of criminal landscape by utilizing statistical analysis and deep learning techniques //Journal of Applied Security Research. – 2024. – T. 19. – №. 4. – S. 560-585.
22. Mukherjee, K. et al. Uncovering spatial patterns of crime: A case study of Kolkata //Crime Prevention and Community Safety. – 2024. – T. 26. – №. 1. – S. 47-90.
23. Saunders, J., Hunt P., Hollywood, J. S. Predictions put into practice: a quasi-experimental evaluation of Chicago’s predictive policing pilot //Journal of experimental criminology. – 2016. – T. 12. – №. 3. – S. 347-371
24. Singh, A. et al. An introduction on the impact of artificial intselligence (ai) in forensic science: a study on the role of ai in crime prevention //Dinesh, An introduction on the impact of artificial intselligence (ai) in forensic science: a study on the role of ai in crime prevention (October 25, 2024). – 2024.
25. van Sleeuwen S. E. M., Ruiter, S., Steenbeek, W. Right place, right time? Making crime pattern theory time-specific //Crime Science. – 2021. – T. 10. – №. 1. – S. 2.
26. Yang, S. et al. The impact of surveillance cameras and community safety activities on crime prevention: Evidence from Kakogawa City, Japan //Sustainable Cities and Society. – 2024. – T. 115. – S. 105858.
27. Zeng, M., Mao, Y., Wang, C. The relationship between street environment and street crime: A case study of Pudong New Area, Shanghai, China //Cities. – 2021. – T. 112. – S. 103143.
