The accurate cost estimation of a construction project in the early stage plays a very important role in successfully completing the project. In the initial stage of construction, when the information necessary to predict construction cost is insufficient, a machine learning model using past data can be an alternative. We suggest a two-level stacking heterogeneous ensemble algorithm combining RF, SVM and CatBoosting. In the step of training the base learner, the optimal hyperparameter values of the base learners were determined using Bayesian optimization with cross-validation. Cost information data disclosed by the Public Procurement Service in South Korea are used to evaluate ML algorithms and the proposed stacking-based ensemble model. According to the analysis results, the two-level stacking ensemble model showed better performance than the individual ensemble models.

In a construction project, construction cost estimation is very important, but construction costs are affected by various factors, so they are difficult to predict accurately. However, with the recent development of ANN technology, it has become possible to predict construction costs with consideration of various influencing factors. Unlike previous research cases, this study aimed to predict the total construction cost by predicting seven sub-construction costs using a multioutput regression model, not by predicting a single total construction cost. In addition, analysis of the change in construction cost prediction performance was conducted by scaling and regularization. We estimated the error rate of predicting construction costs through sub-construction cost prediction to be 16.80%, a level similar to that of the total construction cost prediction error rate of 17.67%. This study shows that the construction cost can be calculated by predicting detailed cost factors at once, and it is expected that various types of construction costs or partial construction costs can be predicted using the predicted detailed cost elements. As a result of predicting several sub-construction costs using multioutput-based ANN, it was found that the prediction error rate varies depending on the type of construction. To improve accuracy, it is necessary to supplement influencing factors suitable for the construction features.

In the planning and design stage, it is difficult to accurately predict construction costs only by estimating approximate cost. It is also very difficult to predict the change in construction costs whenever the design changes. However, using the BIM model’s attribute information and machine learning techniques, accurate construction costs can be predicted faster than when using the existing approximate cost estimate. In this study, building information such as ‘total area’, ‘floor water’, ‘usage’, and BIM attribute information such as ‘wall area’, ‘wall water’, and ‘floor circumference’ were used together to predict construction costs in the schema design stage. As a result of applying the machine learning technique using both the building design information and the BIM model attribute information, it was found that the construction cost was improved compared to the result of individual predictions of the building information or BIM attribute information. While accurately predicting construction costs using BIM’s attribute information has its limits, it is expected to provide more accuracy compared to predicting costs solely based on construction cost influencing factors.

Accurately predicting construction costs during the initial planning stages is crucial for the successful completion of construction projects. Recent advancements have introduced various machine learning-based methods to enhance cost estimation precision. However, the accumulation of authentic construction cost data is not straightforward, and existing datasets frequently exhibit a notable presence of missing values, posing challenges to precise cost predictions. This study aims to analyze diverse substitution methods for addressing missing values in construction cost data. Additionally, it seeks to evaluate the performance of machine learning models in cost prediction through the removal of conditional outliers. The primary goal is to identify and propose optimal strategies for handling missing value in construction cost records, ultimately improving the reliability of cost predictions. According to the analysis results, among single imputation methods, median imputation emerges as the most suitable, while among multiple imputation methods, lasso regression imputation produces the most superior outcomes. This research contributes to enhancing the trustworthiness of construction cost predictions by presenting a pragmatic approach to managing missing data in construction cost performance records, thereby facilitating more precise project planning and execution.

A construction project is often uncertain and plans change frequently, so it is usually difficult to make a reliable and feasible plan. With the development of BIM technology, the future of the construction project can be simulated visually and a more reliable plan can be made. However, with BIM technology data production efficiency is low, since the data is utilized only for animation and visual presentation. Furthermore, although various construction simulation systems have been developed, these systems pose difficulties in terms of measuring performance. In this study, a methodology for analyzing the performance of a 4D building construction simulation system after defining the work process and standard scenario is proposed. the proposed methodology was verified by comparing the performance of the newly developed building construction simulation system and that of an existing commercial building construction simulation system.

The steel fabrication and installation works in a steel-structured building project account for 20% of the entire construction cost. In estimating construction costs, a few parameters are more significant than work item productivity. However, the Standardized Productivity (SP) of steel works presented in Poom-Sam, which is the standardized estimating guide system used in the public sector in Korea, has rarely been updated since its establishment in the 1970s. In order to update and improve its structure and figures, 15 construction sites and 5 steel fabrication shops were visited over a period of two years. From the study, it was found that the structure of Poom-Sam was rather complex and outdated and that the average SP of the works analyzed from the research was approximately 85% of the current SP. Moreover, the effect of the productivity differences on total construction cost was approximately 10%. The productivity improvements and amended Work Breakdown Structure (WBS) are attributable to the technology advancements in equipment and construction methods over the past two decades. The results of this study will improve the reliability and accuracy of cost estimation in steel works.