NEURAL NETWORK SYSTEM OF SALES VOLUME FORECASTING OF RESIDENTIAL REAL ESTATE IN THE PRIMARY REGIONAL MARKET

Abstract

When developing the economic part of a construction project, a cash flow model (CF model) is being built, in which it is necessary to take into account all the key factors affecting the overall project management system. An important component in building a CF model is knowing the volume of future sales. Forecasting the volume of sales allows you to predict the income from the implementation of the project and assess its profitability. Currently, construction companies assess sales volume expertly, and the results of the forecast depend on the expert's experience. In order to increase the efficiency of building the CF model, the authors propose a neural network model for predicting the volume of real estate sales, taking into account market factors. The model is based on the Loginom analytical platform, trained and has good predictive properties. The average relative error of forecasting is 6.89\%. The model takes into account statistically significant external and internal factors affecting the volume of real estate sales in the conditions of shared-equity construction in the Chelyabinsk region market.