Operating system

Electrical engineering

Machine learning

Engineering

Industrial engineering

Artificial intelligence

Systems engineering

Data science

Hydropower

Computer science

Operations research

Cost estimate

Estimation

Process (computing)

SN Applied Sciences

Construction cost predictions to reduce time risk assessment are indispensable steps for process of decision-making of managers. Machine learning techniques need adequate dataset size to model and forecast the cost of projects. Therefore, this paper presents analysis and studied manuscripts that proposed for cost estimation with machine learning techniques for the last 30 years. The impact of this manuscript is deep studied of machine learning techniques and applied an analysis methodology in cost estimation based on direct cost and indirect cost of construction projects, which consists of two parts. In the first part, for study the proposals, we focus on collecting related studied from Google Scholar and Science Direct journals. The interested application areas for project cost estimation are building, highway, public, roadway, water-related constructions, road tunnel, railway, hydropower, power plant and power projects. The second part is regarded to the analysis of the proposals. For cost analysis, there are possibilities to consider two approaches as qualitative and quantitative. However, reflect to the machine learning techniques the quantitative approach is studied. In quantitative approach, we categorized the models in three parts, as statistical, analogues and analytical model and analyse them based on their features. Correspondingly, papers have been thoroughly investigated based on the application area, method applied, techniques implemented, journals, which have been published in, and the year of publication. The most important outcome of this study is to find out the different analytics methods and machine learning algorithms to predict the cost estimation of construction and related projects and aid to find out the suitable applied methods.

Cost estimation and prediction in construction projects: a systematic review on machine learning techniques