Russian Federation
Russian Federation
Russian Federation
Russian Federation
In the modern world, where the amount of data grows exponentially, machine learning methods are becoming a key tool for predicting emergencies and incidents. Recently, ensemble algorithms have been actively used to solve such problems. One of the most effective approaches is gradient boosting over decision trees, which combines the flexibility of trees and the power of gradient optimization. This article presents an assessment of the possibilities of using the gradient boosting method over decision trees using the example of emergencies and incidents in the Perm Territory. The main advantages and limitations of the method are presented. The conducted studies have proven the effectiveness of the gradient boosting method over decision trees for emergency forecasting tasks. Its ability to take into account complex dependencies and work with heterogeneous data makes it a powerful tool in the arsenal of analysts and forecasting specialists.
machine learning, modeling, forecasting, quality assessment of decision-making
1. Matveev A.V. Metody modelirovaniya i prognozirovaniya. SPb.: S.-Peterb. un-t GPS MCHS Rossii, 2022. 230 s. ISBN 978-5-907116-73-3. EDN IMLKWS.
2. Matveev A.V., Bogdanova E.M. Klassifikaciya metodov prognozirovaniya chrezvychajnyh situacij // Nacional'naya bezopasnost' i strategicheskoe planirovanie. 2018. № 4 (24). S. 61–70. EDN YTPZYL.
3. Sapozhnikov A.A. Iskusstvennyj intellekt na sluzhbe MCHS Rossii // Grazhdanskaya zashchita. 2023. № 5 (573). S. 28–29.
4. Lucenko S.G., Utkin O.V. Cifrovye tekhnologii Edinoj gosudarstvennoj sistemy preduprezhdeniya i likvidacii chrezvychajnyh situacij: analiz reshenij i perspektivy razvitiya // Prirodnye i tekhnogennye riski (fiziko-matematicheskie i prikladnye aspekty). 2023. № 3 (47). S. 22–28. DOI:https://doi.org/10.61260/2307-7476-2023-3-22-28. EDN VMMDNC.
5. Machine learning in disaster management: recent developments in methods and applications / Linardos V. [et al.] // Machine Learning and Knowledge Extraction. 2022. Vol. 4. № 2. DOI:https://doi.org/10.3390/make4020020.
6. Klyueva I.A. Sovremennye vozmozhnosti i primery vnedreniya mashinnogo obucheniya // Original'nye issledovaniya. 2021. T. 11. № 7. S. 12–32. EDN HBQRYC.
7. Huang D., Wang S., Liu Z. A systematic review of prediction methods for emergency management // International Journal of Disaster Risk Reduction. 2021. Vol. 62. P. 102412. DOI:https://doi.org/10.1016/j.ijdrr.2021.102412.
8. Hancock J.T., Khoshgoftaar T.M. CatBoost for big data: an interdisciplinary review // Journal of Big Data. 2020. Vol. 7. № 1. P. 94. DOI:https://doi.org/10.1186/s40537-020-00369-8.
9. CatBoost model and artificial intelligence techniques for corporate failure prediction / S.B. Jabeur [et al.] // Technological Forecasting and Social Change. 2021. Vol. 166. P. 120658. DOI:https://doi.org/10.1016/j.techfore.2021.120658.
10. Comparison of the CatBoost Classifier with other Machine Learning Methods / A.A. Ibrahim [et al.] // International Journal of Advanced Computer Science and Applications. 2020. Vol. 11. № 11. P. 738–748. DOI:https://doi.org/10.14569/IJACSA.2020.0111190.
11. Borodushko I.V., Matveev A.V. Sovremennye tendencii i strategicheskie celi razvitiya iskusstvennogo intellekta v Rossijskoj Federacii // Nacional'naya bezopasnost' i strategicheskoe planirovanie. 2024. № 2 (46). S. 66–74. DOI:https://doi.org/10.37468/2307-1400-2024-2-66-74. EDN EFWHYT.
