Efficient estimation and optimization of building costs using machine learning

Pham, T.; Le-Hong, Thai; Tran, Xuan-Linh

doi:10.1080/15623599.2021.1943630

Cited by 22 publications

(13 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These results also confirm the findings of recent studies that consider the performance of ensemble models to be better than individual models (Yan et al. , 2020; Pham et al. , 2021).…”

Section: Discussionsupporting

confidence: 91%

“…The present paper's results analysis shows that the performance of the random forest algorithm is more accurate than other learning models, with an error value of 0.14 in the NRSME criterion and 0.19 in the MAPE criterion. These results also confirm the findings of recent studies that consider the performance of ensemble models to be better than individual models (Yan et al, 2020;Pham et al, 2021). This study finds a suitable overlap between machine learning tools (such as Scikit-learn, NumPy, and SciPy libraries in the Python programming language) and case-based reasoning steps.…”

Section: Cost Overrun Estimationsupporting

confidence: 90%

“…In the competitive environment of the construction industry, costs play a key role as a crucial aspect of project management (Noorzai and Golabchi, 2020;Noorzai et al, 2022a). To date, researchers have used a variety of methods and tools, such as neural networks (Karaca et al, 2020;Alex et al, 2010;Petroutsatou et al, 2012;Asghari et al, 2021;Marzouk and Elkadi, 2016), machine learning algorithms (Rafiei and Adeli, 2018;Lowe et al, 2006;Pham et al, 2021), case-based reasoning (CBR) (Ahn et al, 2020;Kim and Kim, 2010;Kwon et al, 2019Kwon et al, , 2020, and time-series models (Moon et al, 2018;Elfahham, 2019), to improve cost overrun estimates and identify influential factors. Conceptual cost estimation precedes capital commitments and must show the desired level of certainty (Baccarini and Love, 2014).…”

Section: Introductionmentioning

confidence: 99%

“…, 2021; Marzouk and Elkadi, 2016), machine learning algorithms (Rafiei and Adeli, 2018; Lowe et al. , 2006; Pham et al. , 2021), case-based reasoning (CBR) (Ahn et al.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Risk-supported case-based reasoning approach for cost overrun estimation of water-related projects using machine learning

Sohrabi

Noorzai

2022

ECAM

View full text Add to dashboard Cite

PurposeThe present study aims to develop a risk-supported case-based reasoning (RS-CBR) approach for water-related projects by incorporating various uncertainties and risks in the revision step.Design/methodology/approachThe cases were extracted by studying 68 water-related projects. This research employs earned value management (EVM) factors to consider time and cost features and economic, natural, technical, and project risks to account for uncertainties and supervised learning models to estimate cost overrun. Time-series algorithms were also used to predict construction cost indexes (CCI) and model improvements in future forecasts. Outliers were deleted by the pre-processing process. Next, datasets were split into testing and training sets, and algorithms were implemented. The accuracy of different models was measured with the mean absolute percentage error (MAPE) and the normalized root mean square error (NRSME) criteria.FindingsThe findings show an improvement in the accuracy of predictions using datasets that consider uncertainties, and ensemble algorithms such as Random Forest and AdaBoost had higher accuracy. Also, among the single algorithms, the support vector regressor (SVR) with the sigmoid kernel outperformed the others.Originality/valueThis research is the first attempt to develop a case-based reasoning model based on various risks and uncertainties. The developed model has provided an approving overlap with machine learning models to predict cost overruns. The model has been implemented in collected water-related projects and results have been reported.

show abstract

“…These results also confirm the findings of recent studies that consider the performance of ensemble models to be better than individual models (Yan et al. , 2020; Pham et al. , 2021).…”

Section: Discussionsupporting

confidence: 91%

Section: Cost Overrun Estimationsupporting

confidence: 90%

Section: Introductionmentioning

confidence: 99%

“…, 2021; Marzouk and Elkadi, 2016), machine learning algorithms (Rafiei and Adeli, 2018; Lowe et al. , 2006; Pham et al. , 2021), case-based reasoning (CBR) (Ahn et al.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Risk-supported case-based reasoning approach for cost overrun estimation of water-related projects using machine learning

Sohrabi

Noorzai

2022

ECAM

View full text Add to dashboard Cite

show abstract

“…So, in random conditions, the efficiency is a random variable and must be estimated, taking into account the impact of random disturbances on course and results of the project lifecycle implementation [17,18]. This is a process of creating random variables of costs and revenues as well as connected and derived quantities that reflect likely random conditions of the construction project's implementation.…”

Section: Introductionmentioning

confidence: 99%

Randomized Estimation of the Net Present Value of a Residential Housing Development

2021

View full text Add to dashboard Cite

Randomized estimation of the net present value of a housing development allows for the assessment of the efficiency of projects in random implementation conditions. The efficiency of a project is estimated on the basis of primary input data, usually used in project planning. For this purpose, random disturbances are identified that may randomly affect the course and results of the project. The probability and severity of disturbances are determined. The primary initial data is then randomized, and a randomized probabilistic index of the project’s net present value is calculated, the value of which indicates whether the project is profitable or whether implementation should be stopped. Based on this data, the expected total revenue, the expected total cost, the expected gross profit, and the net present value of the randomized performance of the project are calculated. The values of these are estimated for expected, favorable, and unfavorable conditions of implementation. Finally, the risks for the total revenue and total cost of the project are calculated and plotted for comparative revenue values in the range [1, 0] and cost in the range [0, 1]. Their analysis makes it possible to make the right investment decisions before starting the investment at the preparation stage.

show abstract

Applying Machine Learning and Particle Swarm Optimization for predictive modeling and cost optimization in construction project management

almahameed,

Bisharah

2023

Asian J Civ Eng

View full text Add to dashboard Cite

Efficient estimation and optimization of building costs using machine learning

Cited by 22 publications

References 37 publications

Risk-supported case-based reasoning approach for cost overrun estimation of water-related projects using machine learning

Risk-supported case-based reasoning approach for cost overrun estimation of water-related projects using machine learning

Randomized Estimation of the Net Present Value of a Residential Housing Development

Applying Machine Learning and Particle Swarm Optimization for predictive modeling and cost optimization in construction project management

Contact Info

Product

Resources

About