The main idea of this article is the necessity to take into account the multi-variant technological and organizational solutions of individual construction works in order to ensure rational planning for the implementation of construction projects. In practice, selection of construction works most often limited to the evaluation of technological and organizational solutions on the basis of time and cost criteria. However, it should be remembered that construction projects usually have a complex technological and organizational structure. This fact may increase the durations and costs of individual works in relation to their planned durations and costs. Therefore, the authors propose to take into account the criterion of technological and organizational complexity of the assessed construction work. The article describes the procedure for the technological and organizational optimization of construction works. A numerical example of the method of selecting technological and organizational solutions with the use of a fuzzy relation of preferences is also presented. The article also proposes to combine the computational selection model with the network planning model in a graphic form. This approach expands the computational and decision-making possibilities of network models in the practice of planning construction projects.

The homogenous properties – as flats are – have the set of key features that characterizes them. The area of a flat, the number of rooms and storey number where it is located, the technical state of a building, and the state of the vicinity of the blocks of flats assessed. The database comprises 222 flats with their transaction prices on the secondary estate market. The analysed flats are located in a certain quarter of Wrocław city in Poland. The database is large enough to apply machine learning for successful price predictions. Their close locations significantly lower the influence of clients’ assessments of the attractiveness of the location on the flat’s price. The hybrid approach is applied, where classifying precedes the solution of the regression problem. Dependently on the class of flats, the mean absolute percentage error achieved through the calculations presented in the article varies from 4,4 % to 7,8 %. In the classes of flats where the number of cases doesn’t allow for machine predicting, multivariate linear regression is applied. The reliable use of machine learning tools has proved that the automated valuation of homogenous types of properties can produce price predictions with the error low enough for real applications.