Estimation of parameters for a cluster-based piecewise linear risk regression function
- Авторлар: Noskov S.I.1, Belyaev S.V.1, Chekalova A.R.1
-
Мекемелер:
- Irkutsk State Transport University
- Шығарылым: № 3 (2025)
- Беттер: 17-25
- Бөлім: COMPUTER SCIENCE, COMPUTER ENGINEERING AND CONTROL
- URL: https://journals.rcsi.science/2072-3059/article/view/355035
- DOI: https://doi.org/10.21685/2072-3059-2025-3-2
- ID: 355035
Дәйексөз келтіру
Толық мәтін
Аннотация
Background. The article notes that cluster regression models are highly effective in studying various aspects of the analyzed objects’ functioning, including those related to risk. In particular, the following risk analysis problems are considered: country risk, software project risk, failure risk in urban pipeline networks, groundwater contamination risk, building fire risk, flood risk, and loan default risk. The objective of this work is to develop an algorithmic method for identifying the parameters of a cluster-based piecewise linear risk function. Results. A cluster-based piecewise linear risk function has been constructed for housing prices in the regions of the Siberian Federal District. Independent variables include the prices of bricks, cement, and edged boards. The model demonstrates high approximation accuracy, with an average percentage error of 0.4. Conclusions. The problem of estimating unknown parameters of a cluster-based piecewise linear risk function, with the loss function defined as the sum of absolute approximation errors, has been reduced to a linear Boolean programming problem.
Авторлар туралы
Sergey Noskov
Irkutsk State Transport University
Хат алмасуға жауапты Автор.
Email: sergey.noskov.57@mail.ru
Doctor of engineering sciences, professor, professor of the sub-department of information systems and information security
(15 Chernyshevskogo street, Irkutsk, Russia)Sergey Belyaev
Irkutsk State Transport University
Email: bsv2001@list.ru
Master’s degree student
(15 Chernyshevskogo street, Irkutsk, Russia)Aleksandra Chekalova
Irkutsk State Transport University
Email: chekalova49@gmail.com
Master’s degree student
(15 Chernyshevskogo street, Irkutsk, Russia)Әдебиет тізімі
- Yim J., Mitchell H. Comparison of country risk models: hybrid neural networks, logit models, discriminant analysis and cluster techniques. Expert Systems with Applications. 2005;28(1):137–148.
- Wallace L., Keil M., Rai A. Understanding software project risk: a cluster analysis. Information & Management. 2004;42(1):115–125.
- Wang Z., Li S. Data-driven risk assessment on urban pipeline network based on a cluster model. Reliability Engineering & System Safety. 2020;196:106781.
- Li Y., Wang D., Liu Y., Zheng Q., Sun G. A predictive risk model of groundwater arsenic contamination in China applied to the Huai River Basin, with a focus on the region’s cluster of elevated cancer mortalities. Applied Geochemistry. 2017;77:178–183.
- Xin J., Huang C. Fire risk analysis of residential buildings based on scenario clusters and its application in fire risk management. Fire Safety Journal. 2013;62(A):72–78.
- Lagasio V., Quaranta A.G. Cluster analysis of bank business models: The connection with performance, efficiency and risk. Finance Research Letters. 2022;47(A):102640.
- Zhao J., Jin J., Guo Q., Liu L., Chen Y., Pan M. Dynamic risk assessment model for flood disaster on a projection pursuit cluster and its application. Stochastic Environmental Research and Risk Assessment. 2014;28:2175–2183.
- Xu H., Ma C., Lian J., Xu K., Chaima E. Urban flooding risk assessment based on an integrated k-means cluster algorithm and improved entropy weight method in the region of Haikou, China. Journal of Hydrology. 2018;563:975–986.
- Song Y., Wang Y., Ye X., Wang D., Yin Y., Wang Y. Multi-view ensemble learning based on distance-to-model and adaptive clustering for imbalanced credit risk assessment in P2P lending. Information Sciences. 2020;525:182–204.
- Melnyk O., Petrov I., Melenchuk T., Zaporozhets A., Bugaeva S., Rossomakha O. Maritime Systems, Transport and Logistics. Proceedings of the International Conference. Springer, 2025:89–105.
- Thompson J.R.J., Feng L., Reesor R.M., Grace C. Know Your Clients’ Behaviours: A Cluster Analysis of Financial Transactions. Journal of Risk and Financial Management. 2021;14(2):50.
- Noskov S.I. Identification of parameters of a piecewise linear risk function. Transportnaya infrastruktura Sibirskogo regiona = Transport infrastructure of the Siberian region. 2017;1:417–421. (In Russ.)
- Noskov S.I., Khonyakov A.A. Application of the risk function to modeling economic systems. Yuzhno-Sibirskiy nauchnyy vestnik = South Siberian Scientific Bulletin. 2020;(5):85–92. (In Russ.)
- Noskov S.I. Some forms of cluster piecewise linear regression. In-formatsionnye tekhnologii i matematicheskoe modelirovanie v upravlenii slozhnymi sistemami = Information technology and mathematical modeling in the management of complex systems. 2024;(4):41–44. (In Russ.)
- Noskov S.I. Identification of parameters of a combined piecewise linear regression model. Vestnik Yugorskogo gosudarstvennogo universiteta = Bulletin of Yugra State University. 2022;(4):115–119. (In Russ.)
- Noskov S.I., Belyaev S.V. Evaluation of the consistency of a cluster linear regression model. Vestnik Tekhnologicheskogo universiteta = Bulletin of the Technological University. 2025;28(2):88–91. (In Russ.)
- Certificate of state registration of computer programs № 2015612409. Programma resheniya zadach tselochislennogo lineynogo program-mirovaniya s bulevymi peremennymi = A program for solving integer linear programming problems with Boolean variables. D.O. Esikov, A.N. Ivutin, E.V. Larkin, A.S. Novikov; applicant FGBOU VPO «Tul'skiy gosudarstvennyy universitet». № 2014664144: appl. 30.12.2014: publ. 18.02.2015. (In Russ.)
- Certificate of state registration of computer programs № 2024613846. Programma resheniya zadachi tselochislennogo lineynogo programmirovaniya = A program for solving integer linear programming problems. N.A. Egorov; applicant AO «Kontsern vozdushno-kosmicheskoy oborony «Almaz – Antey». № 2024612585: appl. 09.02.2024: publ. 16.02.2024. (In Russ.)
- Shipitsyna R.E., Vitvitskiy E.E. Comparison of the usability of software products for solving the transport linear programming problem: LPSolve IDE and Microsoft Excel. Obrazovanie. Transport. Innovatsii. Stroitel'stvo: sb. tr. V Nats. nauch.-prakt. konf. = Education. Transport. Innovation. Construction: proceedings of the 5th National scientific and practical conference. Omsk, 2022:250–254. (In Russ.)
- Voloshinov V.V., Smirnov S.A. Performance evaluation of the coarse-grained branchand- bound algorithm in the EVEREST computing environment. Programmnye sistemy: teoriya i prilozheniya = Software systems: theory and applications. 2017;8(1):105–119. (In Russ.)
- Federal'naya sluzhba gosudarstvennoy statistiki = Federal State Statistics Service. (In Russ.) Available at: https://rosstat.gov.ru/ (accessed 03.04.2025).
- Edinaya mezhvedomstvennaya informatsionno-statisticheskaya sistema (EMISS) = Unified Interdepartmental Information and Statistical System. (In Russ.). Available at: https://www.fedstat.ru/ (accessed 03.04.2025).
Қосымша файлдар

