Model for determining change of construction duration of large-panel residential buildings

The article considers the issue of assessing the influence of factors on the duration of construction of large-panel residential buildings. Factors influencing the duration of construction were identified in the process of construction of large-panel residential buildings. The identified factors are systematized into 6 groups: technical, technological, organizational, natural and climatic, design, economic. An experiment planning matrix was constructed and an expert assessment of factor groups was performed at the corresponding points of the plan. The coefficients of the regression equation for assessing the influence of factor groups on the construction duration were obtained. As a result of the analysis of the obtained model according to the Fisher criterion, its inadequacy was revealed. The study included a literature review of machine learning models designed to solve forecasting problems in the construction industry. An expert assessment of significant factors for 20 large-panel residential buildings was performed. In order to obtain the most adequate model of the process under study, data processing was performed using artificial neural networks. As a result of the research, a machine learning model was obtained to determine changes in the duration of construction of large-panel residential buildings under the influence of destabilizing factors. The resulting model can be useful both to the technical customer when making decisions about the construction of the facility, and to the general designer when justifying the adopted construction duration.