A model utilizing the artificial neural network in cost estimation of construction projects in Jordan

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Dareen Ryied Al-Tawal ◽  
Mazen Arafah ◽  
Ghaleb Jalil Sweis
Keyword(s):  
Cost Estimation ◽  
Construction Projects ◽  
Building Design ◽  
Management Tool ◽  
Design Stage ◽  
Concept Design ◽  
Ann Model ◽  
Content Type ◽  
Artificial Neural ◽  
Design Factors

PurposeCost estimation is one of the most significant steps in construction planning, which must be undertaken in the preliminary stages of any project; it is required for all projects to establish the project's budget. Confidence in these initial estimates is low, primarily due to the limited availability of suitable data, which leads the construction projects to frequently end up over budget. This paper investigated the efficacy of artificial neural networks (ANNs) methodologies in overcoming cost estimation problems in the early phases of the building design process.Design/methodology/approachCost and design data from 104 projects constructed over the past five years in Jordan were used to develop, train and test ANN models. At the detailed design stage, 53 design factors were utilized to develop the first ANN model; then the factors were reduced to 41 and were utilized to develop the second predictive model at the schematic design stage. Finally, 27 design factors available at the concept design stage were utilized for the third ANN model.FindingsThe models achieved average cost estimation accuracy of 98, 98 and 97% in the detailed, schematic and concept design stages, respectively.Research limitations/implicationsThis paper formulated the aims and objectives to be applicable only in Jordan using historical data of building projects.Originality/valueThe ANN approach introduced as a management tool is expected to provide the stakeholders in the engineering business with an indispensable tool for predicting the cost with limited data at the early stages of construction projects.

An integrated BIM-based approach for cost estimation in construction projects

2020 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Abdulwahed Fazeli ◽  
Mohammad Saleh Dashti ◽  
Farzad Jalaei ◽  
Mostafa Khanzadi
Keyword(s):  
Cost Estimation ◽  
Construction Projects ◽  
Design Methodology ◽  
Automated System ◽  
Design Stage ◽  
Complex Structures ◽  
Human Errors ◽  
Content Type ◽  
The Cost ◽  
Practical Implications

PurposeAnalyzing different scenarios at the design stage of construction projects has always been a challenging task. One of the main parameters that helps owners in making better decisions in designing their buildings is to look after the cost perspective on different design scenarios. Thus, this study aims to propose a semi-automated BIM-based cost estimation approach that enables practitioners to estimate the cost of projects based on different design scenarios by an accurate and agile system.Design/methodology/approachThis study proposes an integrated framework, through which the cost estimation standard of Iran (FehrestBaha) is linked to the materials quantity take-offs (QTO) from BIM models. The performance of the system is based on connecting the classification standards of UniFormat and MasterFormat to the cost estimation standard of FehrestBaha. A BIM-based extension in the Revit environment is developed to automate the cost estimation process.FindingsTo evaluate the efficiency of the proposed approach in cost estimation, it is implemented to estimate the cost of the architectural discipline in a real construction project. The results indicate that the proposed BIM-based approach estimated the cost of the architectural discipline with an acceptable level of accuracy.Practical implicationsThe proposed approach could be used by practitioners to have an agile and accurate BIM-based cost estimation of different scenarios during design process. The semi-automated system considerably reduces the time of cost estimation in comparison to the traditional manual approaches, particularly in complex structures. Owners are able to easily trace changes in project cost according to any changes in components and materials of the BIM model. Furthermore, the proposed approach provides a practical roadmap for BIM-based cost estimation based on cost estimation standards in different countries.Originality/valueUnlike the traditional manual cost estimation approaches, the proposed BIM-based approach is not highly dependent on the knowledge of experienced estimators, which therefore facilitates its implementation. Furthermore, automating both QTO process and the required calculations in this approach increases the accuracy of cost estimation while decreasing the probability of human errors or omission occurrence.

Cost estimation for electric light and power elements during building design

2015 ◽  
Vol 22 (2) ◽  
pp. 190-213 ◽  
Author(s):  
Ajibade A. Aibinu ◽  
Dharma Dassanayake ◽  
Toong-Khuan Chan ◽  
Ram Thangaraj
Keyword(s):  
Regression Models ◽  
Building Design ◽  
Viable Alternative ◽  
Design Stage ◽  
Medium Size ◽  
Content Type ◽  
Ann Modeling ◽  
Covered Area ◽  
Ann Models ◽  
The Cost

Purpose – The study reported in this paper proposed the use of artificial neural networks (ANN) as viable alternative to regression for predicting the cost of building services elements at the early stage of design. The purpose of this paper is to develop, test and validate ANN models for predicting the costs of electrical services components. Design/Methodology/Approach – The research is based on data mining of over 200 building projects in the office of a medium size electrical contractor. Of the over 200 projects examined, 71 usable data were found and used for the ANN modeling. Regression models were also explored using IBM Statistical Package for Social Sciences Statistics Software 21, for the purpose of comparison with the ANN models. Findings – The findings show that the cost forecasting models based on ANN algorithm are more viable alternative to regression models for predicting the costs of light wiring, power wiring and cable pathways. The ANN prediction errors achieved are 6.4, 4.5 and 4.5 per cent for the three models developed whereas the regression models were insignificant. They did not fit any of the known regression distributions. Practical implications – The validated ANN models were converted to a desktop application (user interface) package – “Intelligent Estimator.” The application is important because it can be used by construction professionals to reliably and quickly forecast the costs of power wiring, light wiring and cable pathways using building variables that are readily available or measurable during design stage, i.e. fully enclosed covered area, unenclosed covered area, internal perimeter length and number of floors. Originality/value – Previous studies have concluded that the methods of estimating the budget for building structure and fabric work are inappropriate for use with mechanical and electrical services. Thus, this study is unique because it applied the ANN modeling technique, for the first time, to cost modeling of electrical services components for building using real world data. The analysis shows that ANN is a better alternative to regression models for predicting cost of services elements because the relationship between cost and the cost drivers are non-linear and distribution types are unknown.

scholarly journals Implementation of MCA Method for Identification of Factors for Conceptual Cost Estimation of Residential Buildings

2013 ◽  
Vol 8 (1) ◽  
pp. 25-34 ◽  
Author(s):  
Michał Juszczyk ◽  
Agnieszka Leśniak ◽  
Krzysztof Zima
Keyword(s):  
Comparative Analysis ◽  
Cost Estimation ◽  
Construction Projects ◽  
Residential Buildings ◽  
Residential Building ◽  
Design Stage ◽  
Problem Solution ◽  
Key Factors ◽  
Early Design Stage ◽  
Select Group

Abstract Conceptual cost estimation is important for construction projects. Either underestimation or overestimation of building raising cost may lead to failure of a project. In the paper authors present application of a multicriteria comparative analysis (MCA) in order to select factors influencing residential building raising cost. The aim of the analysis is to indicate key factors useful in conceptual cost estimation in the early design stage. Key factors are being investigated on basis of the elementary information about the function, form and structure of the building, and primary assumptions of technological and organizational solutions applied in construction process. The mentioned factors are considered as variables of the model which aim is to make possible conceptual cost estimation fast and with satisfying accuracy. The whole analysis included three steps: preliminary research, choice of a set of potential variables and reduction of this set to select the final set of variables. Multicriteria comparative analysis is applied in problem solution. Performed analysis allowed to select group of factors, defined well enough at the conceptual stage of the design process, to be used as a describing variables of the model.

scholarly journals Using LOD in Structural Cost Estimation during Building Design Stage: Pilot Study

2014 ◽  
Vol 85 ◽  
pp. 543-552 ◽  
Author(s):  
Jamin Wood ◽  
Kriengsak Panuwatwanich ◽  
Jeung-Hwan Doh
Keyword(s):  
Pilot Study ◽  
Cost Estimation ◽  
Building Design ◽  
Design Stage

Application of artificial neural network to loan recovery prediction

2016 ◽  
Vol 9 (2) ◽  
pp. 222-238 ◽  
Author(s):  
Amos Olaolu Adewusi ◽  
Tunbosun Biodun Oyedokun ◽  
Mustapha Oyewole Bello
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Interest Rates ◽  
Classification Accuracy ◽  
Learning Algorithm ◽  
Type I ◽  
Ann Model ◽  
Content Type ◽  
Credit Evaluation ◽  
Artificial Neural

Purpose This study assesses the classification accuracy of an artificial neural network (ANN) model. It examines the application of loan recovery probability rather than odds of default as the case with traditional credit evaluation models. Design/methodology/approach Data on 2,300 loans granted over the period 2001-2012 was obtained from the databases of Nigerian commercial banks and primary mortgage institutions. A multilayer feed-forward ANN model with back-propagation learning algorithm was developed having classified the sample into training (38 per cent), testing (41 per cent) and validation (21 per cent) sub-samples. Findings The model exhibits a high overall percentage classification accuracy of 92.6 per cent. It also achieves relatively low misclassification Type I and Type II errors at 6.5 per cent and 8.2 per cent, respectively. Macroeconomic variables such as gross domestic product, inflation and interest rates have the strongest influence on the ANN model classification power. The result of the analysis shows that adopting odds of recovery in ANN classification models can lead to improved loan evaluation. Originality/value The paper is distinct from extant studies in that it presents a new dimension to loan evaluation in Nigerian lending market. To the best knowledge of the authors, the paper is among the first to explore probability of loan recovery as the basis for credit evaluation in the country.

scholarly journals Exploring the design risk factors for modular integrated construction projects

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Ibrahim Yahaya Wuni ◽  
Geoffrey Qiping Shen ◽  
Maxwell Fordjour Antwi-Afari
Keyword(s):  
Risk Factors ◽  
Construction Projects ◽  
Relevant Literature ◽  
Uncertain Data ◽  
System Thinking ◽  
Design Stage ◽  
Data Set ◽  
Research Attention ◽  
Content Type ◽  
Knowledge Based

Purpose Modular integrated construction (MiC) is considered as a process innovation to improve the performance of construction projects. However, effective delivery of MiC projects requires management of risks and uncertainties throughout its delivery chain. Although the design stage of MiC projects is usually managed with limited knowledge based on highly uncertain data and associated with epistemic uncertainties, MiC design risks have not received adequate research attention relative to other stages. The purpose of this paper is to conduct a knowledge-based evaluation and ranking of the design risk factors (DRFs) for MiC projects. Design/methodology/approach The paper reviewed the relevant literature to identify potential DRFs and validated their relevance through pilot expert review. The paper then used questionnaires to gather data from international MiC experts from 18 countries and statistically analyzed the data set. Findings Analysis results showed that the five most significant DRFs for MiC projects include unsuitability of design for the MiC method; late involvement of suppliers, fabricators and contractors; inaccurate information, defective design and change order; design information gap between the designer and fabricator; and lack of bespoke MiC design codes and guidelines. A correlation analysis showed that majority of the DRFs have statistically significant positive relationships and could inform practitioners on the dynamic links between the DRFs. Practical implications The paper provides useful insight and knowledge to MiC practitioners and researchers on the risk factors that could compromise the success of MiC project designs and may inform design risk management. The dynamic linkages among the DRFs instruct the need to adopt a system-thinking philosophy in MiC project design. Originality/value This paper presents the first study that specifically evaluates and prioritizes the risk events at the design stage of MiC projects. It sets forth recommendations for addressing the identified DRFs for MiC projects.

Study on Design Support Method Considering the Interaction Among Multi-Variables

2008 ◽  
Author(s):  
Junya Noda ◽  
Qiang Yu
Keyword(s):  
Graphical Model ◽  
Simulation Models ◽  
Hierarchical Cluster ◽  
Design Stage ◽  
Concept Design ◽  
Design Quality ◽  
Detailed Design ◽  
Design Support ◽  
Characteristic Values ◽  
Design Factors

Recently, a remarkable shortening of the development and design period becomes possible by the development of CAE and the optimization technologies, and efficient improvement of design quality in the detailed design stage has been achieved. Nevertheless, it is thought that there is a limit to for this kind of improvement in the near future, no matter how much the upgrade of the detailed design stage will be attempted. Therefore, the technology requested in the next step should be a new approach that can improve the quality of design concept and the efficiency of the concept design processes. For the engineers to improve concept design efficiency, they are requested that they should have very good understanding about the physics of their objectives and special experience about know-how for forming the answers to a very complicated problems. Thus, it is necessary to know the complicated physical relation between the design factors and the evaluation characteristic values to upgrade the concept design stage. It is thought that it can make a further improvement on the efficiency of design process if the technique, which can help the engineers to grip this relation, is established. However, it is very difficult for the engineers to understand a real complicated problem by few experiences. There are a lot of reasons for this kind of problems. For example, there will be a various patterns of design factors that achieve the similar design results, if the design factors have strong interacting relation between each other. In this study, the authors proposed a design support method for extracting the relation between the design factors and the evaluation characteristic values by using the results obtained by simulation models, and it was applied to the vehicle design problems in considering the interaction among the multi-variables by using a hierarchical cluster analysis and a graphical model. It was shown that the results given by the proposed approach can help the engineers to find and understand the essence of the phenomena involved.

Examining barriers for the utilization of non-traditional cost estimating models in developing countries

2018 ◽  
Vol 16 (6) ◽  
pp. 814-827
Author(s):  
Bismark Agyekum ◽  
Ernest Kissi ◽  
Daniel Yamoah Agyemang ◽  
Edward Badu
Keyword(s):  
Cost Estimation ◽  
Construction Projects ◽  
Policy Formulation ◽  
Cost Models ◽  
Cost Estimating ◽  
Estimation Model ◽  
Building Projects ◽  
Content Type ◽  
Expert’S Opinion ◽  
Cost Estimation Model

Purpose Cost estimation model serves as a framework for forecasting the probable cost of proposed construction projects. It can be classified either as traditional or non-traditional depending on the cost variables formulation. However, in the building industry, quantity surveyors traditionally estimate the initial cost of building projects using the traditional models, which have been criticized overtime for its inaccuracies. This paper therefore aims to examine barriers for the utilization of non-traditional cost estimating models. Design/methodology/approach By using a questionnaire survey, respondents were invited to rate their level of agreement on 23 barriers identified from literature and interview (expert’s opinion). Findings Based on factor analysis inefficient techniques, perceptions of model techniques, unavailability of cost data and lack of understanding and unstable economic conditions were identified as barriers to the utilization of non-traditional cost estimating models. Practical/implications Findings demonstrate that there is need for quantity surveyors to get adapted to utilization of non-traditional cost models which offers better accuracies than the traditional approaches in their quest to improve their professional practices. Originality/value This study demonstrates that there are barriers to the utilization of non-traditional cost estimating models in the Ghanaian construction industry, as evident of this will help in policy formulation for the improvement cost estimating practices.

scholarly journals ANN Based Approach for Estimation of Construction Costs of Sports Fields

Complexity ◽  
2018 ◽  
Vol 2018 ◽  
pp. 1-11 ◽  
Author(s):  
Michał Juszczyk ◽  
Agnieszka Leśniak ◽  
Krzysztof Zima
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Cost Estimation ◽  
Construction Projects ◽  
Construction Costs ◽  
General Applicability ◽  
Artificial Neural ◽  
Multilayer Perceptron Networks ◽  
Cost Of Construction ◽  
Sports Fields

Cost estimates are essential for the success of construction projects. Neural networks, as the tools of artificial intelligence, offer a significant potential in this field. Applying neural networks, however, requires respective studies due to the specifics of different kinds of facilities. This paper presents the proposal of an approach to the estimation of construction costs of sports fields which is based on neural networks. The general applicability of artificial neural networks in the formulated problem with cost estimation is investigated. An applicability of multilayer perceptron networks is confirmed by the results of the initial training of a set of various artificial neural networks. Moreover, one network was tailored for mapping a relationship between the total cost of construction works and the selected cost predictors which are characteristic of sports fields. Its prediction quality and accuracy were assessed positively. The research results legitimatize the proposed approach.

Sign in / Sign up

Export Citation Format

Share Document