BACK
- RESEARCH AND DESIGN CENTER "CITY DEVELOPMENT" - CONSTRUCTION COMPLEX
- Forecasting The Terms Of Renovation Of Existing Residential Development
- UDC 69.003:658.012.22
doi: 10.33622/0869-7019.2024.11.22-26
Sergey A. SEMENOV1,2, s.semenov@dev-city.ru
Yaroslav S. ARGUNOV3, argunov8@yandex.ru
1 Research and Design Center "City Development", prospekt Mira, 19, str. 3, Moscow 129090, Russian Federation
2 National Research Moscow State Civil Engineering University, Yaroslavskoye shosse, 26, Moscow 129337, Russian Federation
3 Northeastern University, 360 Huntington Avenue, Boston, Massachusetts 02115, USA
Abstract. The possibilities of using predictive analytics methods to forecast the timing of project implementation during the renovation of existing residential deelopment are considered. The key methods of predictive analytics are shown, as well as the features of using the method of forming a model based on ML algorithms (machine learning algorithms). The results of the study and an example of the successful application of the developed model for forecasting project deadlines in the formation of strategic calendar schedules for the implementation of the Moscow Housing Renovation Program are presented. The use of models generated using ML technologies makes it possible to accurately predict the timing of the implementation of measures, which makes it possible to use them when building consolidated calendar schedules and make long-term schedules for the resettlement of residents, schedules for the need for construction equipment and building materials, as well as to form benchmarks for evaluating the effectiveness of the program.
Keywords: predictive analytics, neural network, TensorFlow, calendar planning, deadlines for renovation projects, duration of construction - REFERENCES
1. Kievskiy L. V., Kievskiy I. L. Teoriya renovatsii [Renovation theory]. Moscow, Stolitsa Publ., 2023. 528 p. (In Russ.).
2. Kolmykov I. A. Predictive analytics and "digital maturity". Informatizatsiya i sistemy upravleniya v promyshlennosti, 2020, no. 6, pp. 50-52. (In Russ.).
3. Kamaeva Yu. V., Adamtsevich L. A. Prospects for the use of predictive analytics in construction. Stroitel'stvo i arkhitektura, 2023, vol. 11, no. 2, pp. 1-11. (In Russ.).
4. Cherkasov D. Yu. Ivanov V. V. Machine Learning. Nauka, tekhnika i obrazovanie, 2018, no. 5, pp. 85-87. (In Russ.).
5. Donskoy V. I. Machine learning and learnability: a comparative overview. Intellectual Archive, 2012, no. 933, pp. 1-19. (In Russ.).
6. Kievskiy I. L., Argunov S. V., Zharov Ya. V., Yurgaytis A. Yu. Algorithmization of planning, management and information processing systems in construction. Promyshlennoe i grazhdanskoe stroitel'stvo, 2022, no. 11, pp. 14-24. (In Russ.). doi: 10.33622/0869-7019.2022.11.14-24
7. Zamakhina D. V., Parkhomenko M. I. The use of calendar planning methods to control the implementation of projects for the planning of renovation territories. Promyshlennoe i grazhdanskoe stroitel'stvo, 2020, no. 11, pp. 56-62. (In Russ.). doi: 10.33622/0869-7019.2020.11.56-62
8. Pudova E. E. A tool for planning and forecasting housing construction. Promyshlennoe i grazhdanskoe stroitel'stvo, 2023, no. 11, pp. 56-59. (In Russ.). doi: 10.33622/0869-7019.2023.11.56-59 - For citation: Semenov S. A., Argunov Ya. S. Forecasting the Terms of Renovation of Existing Residential Development. Promyshlennoe i grazhdanskoe stroitel'stvo [Industrial and Civil Engineering], 2024, no. 11, pp. 22-26. (In Russ.). doi: 10.33622/0869-7019.2024.11.22-26
BACK
