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

Abstract

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.

Modelling the cause and effect relationship risks in reverse logistics supply chains for demolition waste

“…The rationale for selecting the BBN technique is due to its capacity to deal with uncertain and complicated problems (Hon et al, 2021). Such an approach has also been used in previous construction-related research, such as construction productivity prediction through BNN (Khanh et al, 2022); project scheduling and performance prediction (Rezakhani, 2021); predicting the construction project risk (Pan and Zhang, 2021) and risk propagation across the construction supply chain network (Chhimwal et al, 2021). Further, the BN is more suited as it has the ability to express the complex relationships in a network through conditional probability distributions (Rezakhani, 2021).…”

“…Figure 2 could further be deemed as a conceptual framework that captures the two main phases of the research. Recent studies, such as Khanh et al. (2022), have used a similar approach with the literature review for the data collection and identifying of the main critical factors for the BN model development and describing the combination of the different phases as a conceptual framework.…”

Unintended Consequences of Productivity Improvement Strategies on Safety Behaviour of Construction Labourers; A Step toward the Integration of Safety and Productivity

“…Overtime is often preferred for a short period because it improves labour productivity without the coordination and supervision issues associated with shift work and the need for an additional skilled workforce for overmanning [3,99]. However, the implementation of overtime creates further issues, including fatigue, low morale and higher cost per unit [94,100]. According to Mohammadi and Tavakolan [101], the shortterm implementation of overtime will increase productivity despite its long term effect that appears as lost time and growth in the accident rate.…”

“…Shift work is an effective method to accelerate the project subject to being well-planned and implemented for a short duration [95]. The hasty implementation of shift work without proper planning can significantly negatively impact labour productivity [100,102]. Recommendations for achieving the best results include: applying overlap supervision between two shifts; assigning tasks to the second shift team at different locations; planning the sec-ond shift carefully; and, finally, performing a detailed safety evaluation to reduce the risks of working at night [94,95].…”

Research Paradigm of Network Approaches in Construction Safety and Occupational Health

“…However, owing to the differences in research objects and research objectives, the importance of the above four aspects in different studies is slightly different, which needs further discussion. Near-miss falls; construction safety [26] Construction occupational health and safety [55] BN Bayesian network Safety culture; organizational culture; [56] description, explanation, control Chains of unsafe behaviors; building construction; accident prevention [57] Construction safety; safety management; human behavior; safety climate [58] Prefabricated buildings; improved human factor analysis and classification system [59] Operational tunnels [60] Electrical and mechanical (E&M) works; accident analysis [61] explanation, control Bridge construction; fall risks [19] steel construction; fall risks [62] Falling accidents; human-organizational factors [63] description, explanation Construction safety; human error; labor and personnel issues [38] Hydraulic engineering; human error [64] Safety risk analysis; tunnel construction [65] Occupational safety; accident prevention; Falls [18] explanation, prediction Human error; construction industry [66] Productivity; building project; construction management [67] DBN Dynamic Bayesian network Occupational accidents; organization factors [68] explanation, prediction…”