Material resources are one of the main elements of the construction cost estimate. The nomenclature of material resources includes a large number of items. It is impossible to objectively estimate the construction cost, capital construction, and maintenance works without carrying out monitoring of the prices of constructional resources and accounting for these data in estimates. The purpose of the present study consists in developing an engineering approach to the simulation of pricing in the construction materials’ market. To achieve this purpose, we use mathematical statistics methods such as linear regression and autoregressive integrated moving average, as well as machine learning methods, namely gradient boosting and recurrent neural networks. In consequence of this work, we proposed a scheme to store statistical information based on the SpagoBI business intelligence platform, as well as designed hybrid intelligent predictive model, which allowed automating the engineering approach to the prediction of prices and objectifying advanced analytics of the construction materials’ market. The proposed engineering approach allows predicting the dynamics of the construction materials’ market segments when managing the construction cost at the level of enterprise and the region that will enable adequate decision- making in the course of investment projects development.