Using Multivariable Linear Regression Technique for Modeling Productivity Construction in Iraq

Al-Zwainy, Faiq M. S.; Abdulmajeed, Mohammed Hashim; Aljumaily, Hadi Salih Mijwel

doi:10.4236/ojce.2013.33015

Cited by 28 publications

(10 citation statements)

References 24 publications

(16 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

Section: Analysis Resultsmentioning

confidence: 99%

“…There are some commonly used techniques to build a predictive model with high accuracy invented by several previous studies such as regression, learning curve and neural networks. Al-Zwainy et al (2013) indicated that the average error is nearly 4.0% when using multivariable linear regression to model construction productivity. Khanh and Kim (2014) proved that the maximum absolute percentage error (MAPE) of a learning curve-based model is approximately 5.0% for predicting construction productivity for formwork, rebar and concrete activity in high-rise buildings.…”

Section: Validation Of the Accuracy Of Proposed Modelmentioning

confidence: 99%

See 1 more Smart Citation

Construction productivity prediction through Bayesian networks for building projects: case from Vietnam

Khanh

Kim

Linh

2022

ECAM

View full text Add to dashboard Cite

PurposeThis study aims to focus on exploring the construction productivity of building projects under the influence of potential factors. The three primary purposes are (1) determining critical factors affecting construction productivity; (2) identifying causal relationship and occurrence probability of these factors to develop a Bayesian network (BN) model; and (3) validating the accuracy of predictions from the proposed BN model via a case study.Design/methodology/approachA conceptual framework that includes three performance stages was used. Twenty-two possible factors were screened from a comprehensive literature review and evaluated through expert opinions. Data were collected using a structured questionnaire-based survey and case-study-based survey. The sampling methods were based on non-probability sampling.FindingsWorker characteristic-related factors significantly affect labour productivity for a construction task. Construction productivity is dominated by the working frequency of workers (overtime), complexity of the task, level of technology application and accidents. Labour productivity is defined as nearly 50% of the baseline productivity using the BN model created by the caut 2sal relationship and probability of factors. The prediction error of the BN model was 6.6%, 10.0% and 9.3% for formwork (m2/h), reinforcing steel (ton/h) and concrete (m3/h), respectively.Research limitations/implicationsThe evaluation or prediction of productivity performance has become a necessary topic for research and practice.Practical implicationsManagers and practitioners in the construction sector can utilise the outcome of this study to create good productivity management policies for their prospective projects.Originality/valueWorker-related characteristics are dominant among critical factors affecting labour productivity for a construction task; the proposed BN-based predictive model is built based on these critical factors. The BN approach is highly accurate for construction productivity prediction. The findings of this study can fill gaps in the construction management body of knowledge when modelling construction productivity under the effects of multiple factors and using a simple probabilistic graphic tool.

show abstract

Section: Analysis Resultsmentioning

confidence: 99%

Section: Validation Of the Accuracy Of Proposed Modelmentioning

confidence: 99%

Construction productivity prediction through Bayesian networks for building projects: case from Vietnam

Khanh

Kim

Linh

2022

ECAM

View full text Add to dashboard Cite

show abstract

“…The author used the same procedure that was followed by Al-Zwainy et al [3] for exploring the comprehensive survey. The comprehensive survey was collected via previous studies from local and international journal papers, research reports, conference proceedings, theses, dissertations, and Internet publications.…”

Section: Study Methodologymentioning

confidence: 99%

Diagnosing the Causes of Failure in the Construction Sector Using Root Cause Analysis Technique

Al-Zwainy

Mohammed

Varouqa

2018

Journal of Engineering

View full text Add to dashboard Cite

The aim of this study is identifying and diagnosing the causes of construction project failure by using different project management process groups. These groups were initiation process group, planning process group, design process group, contract process group, executing and monitoring process group, and close process group. Also, the relative importance of the causes of construction project failure was investigated. Three techniques were used in this study: Ishikawa diagrams, Pareto diagrams, and 5-why techniques. The results were generally identified and diagnosed thirty-five causes of the construction project failure; however, only twenty-three of the causes were the most important. The majority of causes (thirteen causes) were obtained by using executing and monitoring project management process group. Seven causes were obtained by using contract project management process group. In addition, fewer causes (only three causes) were obtained by using initiation project management process group.

show abstract

“…Regression analyses are among the most widely used models for construction labor productivity prediction. One of the most frequently used among these analyses is linear regression models (Al-Zwainy et al, 2013;Ghodrati et al, 2018;Gurmu and Aibinu, 2017;Hai and Van Tam, 2019). More accurate predictions can be made by reducing variance and bias in linear regression algorithms.…”

Section: Ecam 313mentioning

confidence: 99%

“…Labor productivity plays a fundamental role in building production (Golnaraghi et al, 2020a), because the share of labor productivity is great at every critical stage of the construction process, including cost, time and quality (Al-Zwainy et al, 2013;Mlybari, 2020;Momade et al, 2020). One of the most important reasons for this is that many factors impact labor productivity (Mlybari, 2020).…”

Section: Introductionmentioning

confidence: 99%

Development and comparative of a new meta-ensemble machine learning model in predicting construction labor productivity

Karatas

Budak²

2022

ECAM

View full text Add to dashboard Cite

PurposeThe study is aimed to compare the prediction success of basic machine learning and ensemble machine learning models and accordingly create novel prediction models by combining machine learning models to increase the prediction success in construction labor productivity prediction models.Design/methodology/approachCategorical and numerical data used in prediction models in many studies in the literature for the prediction of construction labor productivity were made ready for analysis by preprocessing. The Python programming language was used to develop machine learning models. As a result of many variation trials, the models were combined and the proposed novel voting and stacking meta-ensemble machine learning models were constituted. Finally, the models were compared to Target and Taylor diagram.FindingsMeta-ensemble models have been developed for labor productivity prediction by combining machine learning models. Voting ensemble by combining et, gbm, xgboost, lightgbm, catboost and mlp models and stacking ensemble by combining et, gbm, xgboost, catboost and mlp models were created and finally the Et model as meta-learner was selected. Considering the prediction success, it has been determined that the voting and stacking meta-ensemble algorithms have higher prediction success than other machine learning algorithms. Model evaluation metrics, namely MAE, MSE, RMSE and R2, were selected to measure the prediction success. For the voting meta-ensemble algorithm, the values of the model evaluation metrics MAE, MSE, RMSE and R2 are 0.0499, 0.0045, 0.0671 and 0.7886, respectively. For the stacking meta-ensemble algorithm, the values of the model evaluation metrics MAE, MSE, RMSE and R2 are 0.0469, 0.0043, 0.0658 and 0.7967, respectively.Research limitations/implicationsThe study shows the comparison between machine learning algorithms and created novel meta-ensemble machine learning algorithms to predict the labor productivity of construction formwork activity. The practitioners and project planners can use this model as reliable and accurate tool for predicting the labor productivity of construction formwork activity prior to construction planning.Originality/valueThe study provides insight into the application of ensemble machine learning algorithms in predicting construction labor productivity. Additionally, novel meta-ensemble algorithms have been used and proposed. Therefore, it is hoped that predicting the labor productivity of construction formwork activity with high accuracy will make a great contribution to construction project management.

show abstract

Using Multivariable Linear Regression Technique for Modeling Productivity Construction in Iraq

Cited by 28 publications

References 24 publications

Construction productivity prediction through Bayesian networks for building projects: case from Vietnam

Construction productivity prediction through Bayesian networks for building projects: case from Vietnam

Diagnosing the Causes of Failure in the Construction Sector Using Root Cause Analysis Technique

Development and comparative of a new meta-ensemble machine learning model in predicting construction labor productivity

Contact Info

Product

Resources

About