Project Cost Estimation Research Articles

Construction Project Cost Prediction Method Based on Improved BiLSTM

In construction project management, accurate cost forecasting is critical for ensuring informed decision making. In this article, a construction cost prediction method based on an improved bidirectional long- and short-term memory (BiLSTM) network is proposed to address the high interactivity among construction cost data and difficulty in feature extraction. Firstly, the correlation between cost-influencing factors and the unilateral cost is calculated via grey correlation analysis to select the characteristic index. Secondly, a BiLSTM network is used to capture the temporal interactions in the cost data at a deep level, and the hybrid attention mechanism is incorporated to enhance the model’s feature extraction capability to comprehensively capture the interactions among the features in the cost data. Finally, a hyperparameter optimisation method based on the improved particle swarm optimisation algorithm is proposed using the prediction accuracy as the fitness function of the algorithm. The MAE, RMSE, MPE, MAPE, and coefficient of determination of the simulated prediction results of the proposed method on the dataset are 7.487, 8.936, 0.236, 0.393, and 0.996%, respectively, where MPE is a positive coefficient. This avoids the serious consequences of underestimating the cost. Compared with the unimproved BiLSTM, the MAE, RMSE, and MAPE are reduced by 15.271, 18.193, and 0.784%, respectively, which reflects the superiority and effectiveness of the method and can provide technical support for project cost estimation in the construction field.

EVALUATION OF COST PERFORMANCE IN THE SUTOJAYAN DISTRICT SUBALI BRIDGE CONSTRUCTION PROJECT (D.G.008), BLITAR REGENCY USING EARNED VALUE ANALYSIS METHOD

One of the project types is the Construction Project. The main activity components of this type of project consist of feasibility assessment, engineering design, procurement and construction. In construction projects very often delays occur where the realization in the field does not match the schedule of the implementation plan, due to several factors that occur, even though a careful plan has been prepared but in practice in the field there are still many problems in implementation. The purpose of this study was to determine the cost and time performance in the implementation that took place from week -1 to week 17 on the Subali Bridge Construction project, Sutojayan Kec. (D.G.008), Blitar Regency using Earned Value. From the results of the analysis it can be seen that the costs incurred are lower than the planned costs, this can be seen in the CPI value of 1.28 while the implementation time is slower than the planned schedule indicated by the SPI value of 0.71. The results of the calculation of the estimated project cost of Rp. 8,214,904,015.36 with a budget plan of Rp. 10,502,000,000.00 there is an efficiency of Rp. 2,287,095.64 (21.78%). with an estimated completion time of 19.43 weeks, indicating that the project is delayed for 2.43 weeks from the planned 17 weeks.

Time series-based Project Cost Forecasting Framework

Current inflation rates have significantly been increasing construction project costs globally. Thus, it is crucial to consider potential inflationary trends when estimating the cost at completion of prolonged projects. However, the absence of literature providing guidance on analyzing inflation trends and adjusting the ongoing project cost performance factor is a gap that needs filling. This study proposes a framework for estimating ongoing project costs based on trend and seasonality analysis of the project cost performance through the Holt-Winters method. The proposed framework also incorporates the estimation of project completion time and is applied to a real case study to assess its efficacy. The results are compared with the ones obtained through pre-existing index-based methods. This paper seeks to improve the accuracy of project cost estimation and management in challenging and uncertain economic environments by providing an alternative to the traditional cost at completion forecasting approach.

Critical Factors Influencing Bid Mark-up Decision in Public Street Project – A Review

Deciding a bid price with an appropriate mark-up added to the estimated project cost is essential for the contractors' business survival. However, the competitive environment had influenced contractors to offer the lowest bid price, leading to the submission of unrealistically low prices to win bids. This practice can impact disputes and adversarial relationships between parties during construction and provide an additional risk to the project delay, cost overrun, quality compromise and failure to complete the project. Therefore, this paper aims to provide an overview of the literature on critical factors influencing bid mark-up decisions in public street projects. The objectives are to identify methods and tools, including the critical factors in determining the contractors' bid mark-up decision. The approach is based on analysing pertinent publications on the theme. The top five (5)ranked factors influencing contractors' decision on bid mark-up size can be found in the literature: the number of bidders, the competitiveness of other bidders, relationship and experience with clients, experience on similar projects and project size. Besides that, the determination of mark-up size is based on experience, intuition, past bidding results, past bidding patterns ofcompetitors, the client's tender estimate, the client's record, and financial ability.

Towards a Framework for Enhancing Construction Project Labour Productivity in Kenya

Based on labor productivity, construction projects in Kenyan cities and beyond will either succeed or fail. Absence or insufficiency of labor productivity management makes it difficult or impossible for clients and contractors to accurately estimate project costs, which causes costs to rise, profits to decline, project execution times to lengthen, projects to stall, and industry confidence to decline. The topic of construction labor productivity is investigated in this exploratory study among Nairobi-based practitioners and on Nairobi-based projects. It defines the word and assesses the body of literature that is currently available. Next, it assesses several facets of labor productivity in building projects and among practitioners. Lastly, it clarifies significant aspects of CLP in the sector.

A data-driven framework for conceptual cost estimation of infrastructure projects using XGBoost and Bayesian optimization

ABSTRACT Cost estimation is a key component of project plans, yet it is challenging to provide reliable and efficient estimations using conventional methods in the conceptual phase of infrastructure projects. This study proposes a framework that integrates feature selection, extreme gradient boosting (XGBoost), Bayesian optimization (BO), and SHapley Additive exPlanations (SHAP) to provide conceptual cost estimations and explain the results for early decision-making. Correlation analysis and forward search are combined to select the key features. XGBoost is developed as the estimator and enhanced by BO in accuracy and efficiency. Model explanations were presented using SHAP. The framework is demonstrated through a case study of electric substations containing 605 samples. The results show that the proposed framework can provide satisfactory performance on conceptual cost estimations, where BO-XGBoost outperforms the benchmark models (with ~0.9567, adjusted ~0.9549, RMSE ~ 0.8690, and MAE ~ 0.4875). SHAP reveals how the features contribute to the cost based on both global and local explanations. The framework provides a guideline for more accurate, efficient, and explainable cost estimations in the conceptual phase of infrastructure projects. It can support the government and project planners in early decision-making, including reliable project budget and plan alternatives selection.

Identifikasi Faktor Yang Mempengaruhi Besaran Biaya Dalam Pelaksanaan Proyek Skala Kecil Di Bali

The realization of the implementation of a project must be within the initial project planning stage. In the planning stage, various types of activities are carried out, starting from forming the project team, preparing the schedule, planning project resources, and preparing project cost estimates. Cost estimation activities are one of the main processes in a construction project to determine the amount of funds that must be provided for a building. Without costs, the project will not be able to be implemented even if other resource elements are met. Costs in construction projects consist of direct costs and indirect costs. Based on these 2 (two) types of costs, research needs to be carried out to determine the factors that influence the nominal amount of these types. Data analysis in this research uses the Analytical Hierarchy Process (AHP) method. The results of the research show that the order of factors that have the most influence on the two types of costs include force majeure factors, availability of labor, detailed design plans, work methods, technical specifications, distance to the place where materials/tools are purchased, location of work/project, the environment around the project, and road conditions leading to the project.

Artificial Neural Networks for Construction Project Cost and Duration Estimation

Artificial Neural Networks for Construction Project Cost and Duration Estimation

İnşaat Maliyet Endeksi Tahmininde Holt-Winters Üstel Düzeltme Parametrelerinin PSO ve İleri Walk-Forward Cross-Validation ile Optimizasyonu

This research aims to enhance the accuracy of Construction Cost Index (CCI) forecasting using Holt-Winters exponential smoothing (ES) by optimizing its parameters, focusing on minimizing the Mean Absolute Percentage Error (MAPE) for precise CCI forecasts. To reach this aim, The Holt-Winters model parameters are optimized through Particle Swarm Optimization (PSO) and Walk-Forward Cross-Validation (WFCV). PSO, a metaheuristic optimization algorithm, is being applied to search for optimal values of the smoothing parameters (alpha, beta, and gamma) that determine the weightage of past observations, trends, and seasonality, respectively. WFCV is assessed the model's performance and ensures robustness. Reduced MAPEs of 22 for CCI forecasts and 2 for training data are the findings of the optimized Holt-Winters model. The obtained alpha, beta, and gamma values are 0.99, 0.77, and 0, respectively, highlighting the importance of while neglecting seasonality. Convergence graphs demonstrate the superiority of the optimization approach over conventional parameter values or random selections. By employing PSO and WFCV, the study efficiently fine-tunes the Holt-Winters model for precise CCI forecasting. Optimized parameter values enable data driven decision-making in construction project cost estimation and budget management. This research contributes a reliable and robust optimization methodology for CCI forecasting, supporting advancements in the field.

Automated system for high-accuracy quantity takeoff using BIM

Reliable construction project cost estimation relies on accurate quantity takeoffs (QTOs), traditionally done with error-prone 2-D drawings, but the emergence of Building Information Modeling (BIM) has improved QTO speed, accuracy, and reliability. However, the quality of BIM models can influence quantity accuracy, an aspect often overlooked in research on automating QTO with BIM. This paper develops an integrated framework to automatically extract and visualize construction quantities from BIM models. The system includes a Quantity Precision Check (QPC) module for automating more accurate QTO outputs. These outputs are then automatically transferred to an external database and visualized through a user-friendly dashboard on the Microsoft Power BI platform. This dashboard allows for comparisons between 2-D and BIM quantities and helps track changes in quantities over time due to design changes. The system was successfully validated in an infrastructure construction project in Canada, where it identified a 39% inconsistency in wall elements' material quantities and reduced steel quantity by 10% due to design changes. Overall, the system offers a speedy, reliable, and efficient tool for construction estimators, site managers, and cost control teams to provide accurate quantities to the procurement team and make swift decisions in response to design change impacts on construction costs.

Performance, processing yields, and fillet composition of specific United States diploid and triploid rainbow trout (Oncorhynchus mykiss) lines reared in a semi-commercial scale freshwater recirculating aquaculture system

Large rainbow trout marketed as steelhead are gaining considerable attention for production in recirculating aquaculture systems (RAS). Diploid and triploid trout with varying genetics are available from several commercial suppliers; however, the performance and processing metrics of these lines have not been compared when raised in freshwater RAS. Current data on these outcomes could support more accurate cost and profitability estimates for potential RAS projects and optimize operation for existing farms. Accordingly, the objective of this study was to quantify performance metrics, processing yield, and fillet composition of six all-female rainbow trout lines (three diploid and three triploid) exposed to an artificial winter (12:12 light: dark at 40 g (Artificial Winter Photoperiod; AWP)) or continuous, 24-h light (No Winter Photoperiod; NWP) grown in a semi-commercial scale freshwater RAS to 3.5 kg. Overall, growth was impacted by line, ploidy, and artificial winter photoperiod. Diploid and AWP trout were smaller than triploids and NWP trout at stocking and 500 g. Mean diploid and triploid weight was similar at larger sizes (>1 kg); however, triploid performance compared to diploids varied by commercial supplier. Mortality was lower in lines from commercial supplier 1 than lines from commercial supplier 2 and the United States Department of Agriculture (14.4 ± 0.8 vs 27.5 ± 2.0 and 29.8 ± 4.3%, respectively). Head-on gutted and skin-on fillet yields were related with larger fish weight. Mature prevalence in diploids may have led to differences observed between diploids and triploids in fillet lipid (10.9 ± 0.8 vs 13.3 ± 0.6%) and moisture (67.0 ± 0.6 vs 65.1 ± 0.4%). The results provide guidance for rainbow trout RAS producers to make informed decisions on optimal harvest size targets and tailor their rainbow trout line or ploidy selection to those harvest sizes.

Improvement of pricing in the construction industry: Integrating information modeling technologies and transitioning regions to the resource index method

Ensuring accurate cost estimation for project implementation, while accounting for regional specifics, is a crucial task for pricing practices in the construction industry. To address this challenge, the transition from the base index method with cost item indexation to the resource index method for estimating project costs is planned in the 1st quarter of 2023. Additionally, starting from 2024, the mandatory use of information modeling technologies for project design will be implemented. This article examines the rationale behind implementing modifications in the pricing system, outlines the algorithm for estimating costs using the resource index method, identifies the advantages and challenges associate with this new approach, and highlights the prospects of integrating information modeling technologies. The study employs comparative and statistical analysis, as well as methods of synthesis and systematization of information. The analysis of data from the Federal State Information System of Pricing in Construction (TsS FSIS) focuses on regions that have already transitioned to the resource index method. On the basis of the research findings, the article reveals the issues related to the adoption of alternative cost estimation methods in a region. It also proposes approaches for enhancing the pricing system to effectively apply the resource index method for cost estimation in construction projects, while incorporating the use of information modeling technologies (IMT).

A bibliometric review of the statistical modelling techniques for cost estimation of infrastructure projects

PurposeCost overrun in infrastructure projects is a constant concern, with a need for a proper solution. The current estimation practice needs improvement to reduce cost overruns. This study aimed to find possible statistical modelling techniques that could be used to develop cost models to produce more reliable cost estimates.Design/methodology/approachA bibliographic literature review was conducted using a two-stage selection method to compile the relevant publications from Scopus. Then, Visualisation of Similarities (VOS)-Viewer was used to develop the visualisation maps for co-occurrence keyword analysis and yearly trends in research topics.FindingsThe study found seven primary techniques used as cost models in construction projects: regression analysis (RA), artificial neural network (ANN), case-based reasoning (CBR), fuzzy logic, Monte-Carlo simulation (MCS), support vector machine (SVM) and reference class forecasting (RCF). RA, ANN and CBR were the most researched techniques. Furthermore, it was observed that the model's performance could be improved by combining two or more techniques into one model.Research limitations/implicationsThe research was limited to the findings from the bibliometric literature review.Practical implicationsThe findings provided an assessment of statistical techniques that the industry can adopt to improve the traditional estimation practice of infrastructure projects.Originality/valueThis study mapped the research carried out on cost-modelling techniques and analysed the trends. It also reviewed the performance of the models developed for infrastructure projects. The findings could be used to further research to develop more reliable cost models using statistical modelling techniques with better performance.

Analyzing Cost Risk Indicators for Enhancing Construction Project Delivery Performance

Risk factors are an inherent component of construction projects, and sometimes, it is difficult to completely eliminate these risks without proper management. This research focused on investigating cost-related risk indicators influencing the performance of construction projects in insurgency-affected areas such as Maiduguri. The assessment employed the Relative Importance Index (RII) and Exploratory Factor Analysis (EFA) to gauge the likelihood of these risks. Data was collected via a questionnaire from construction professionals, including clients, consultants, contractors, and subcontractors. The results analyzed through statistical software revealed that key drivers of cost-related risks were safety and environmental factors, physical threats, disasters, force majeure events, and economic risk factors. The top five most probable risks included costs related to insurgency damages, financial limitations due to insurgency, oversights caused by the insurgency, price increases due to attacks, and labour shortages. Conversely, risks related to cash flow issues and project cost estimation errors were less common. The findings suggest that professionals who consider these specific risk factors when devising risk management strategies can enhance the accuracy of their risk assessments and cost projections.

Energy financing, energy projects retrofit and energy poverty: a scenario-analysis approach for energy project cost estimation and energy price determination.

The research aims to determine the nexus of energy projects retrofit and poverty under two scenarios: energy project cost estimation and energy price determination. Households in rural areas of northern China are now required to switch from coal to cleaner heating options, including natural gas and electricity, as part of a government-led clean heating initiative. This initiative significantly increased the heating expense for participating homes, even when substantial subsidies were applied. We surveyed a large number of northern Chinese households to learn more about the rise in energy insecurity that has been attributed to government action. Our research shows that switching to electricity and gas from coal considerably worsens energy poverty in several ways, whereas switching to clean coal improves the situation. According to an econometric study, changes in energy poverty reveal heterogeneity in several ways. There is little change in Beijing, while the considerably less developed province of Hebei to the north sees a 75% rise. Energy poverty is more common in families with poorer incomes, lower levels of education, and smaller sizes. People who lack resources to insulate their homes will feel the effects more acutely. These results support the idea that low-income families would suffer disproportionately under a "one policy for all" mandate. For policymakers working on energy transition strategies for a low-carbon economy, it highlights the need to consider the distributional impact.

A machine learning study to improve the reliability of project cost estimates

Project managers need reliable predictive analytics tools to make effective project intervention decisions throughout the project life cycle. This study uses Machine learning (ML) to enhance the reliability in project cost forecasting. A XGBoost forecasting model is developed and computational experiments are conducted using real data of 110 projects representing 1268 cost data points. The developed model performs better than some Earned value management (EVM), ML (Random forest, Support vector regression, LightGBM, and CatBoost), and non-linear growth (Gompertz and Logistic) models. The model produces more accurate estimates at the early, middle, and late stages of the project execution, allowing for early warning signals for more effective cost control. In addition, it shows more accurate estimates in most projects tested, suggesting consistency when repeatedly used in practice. Project forecasting studies mainly used ML to estimate the project duration; a few ML studies estimated the project cost at the project’s conceptual stage. This study uses real data and EVM metrics, proposing an effective XGBoost model for forecasting the cost throughout the project life cycle.

Models to Analyze Risk in Time and Cost Estimation of Tunneling Projects

Time and cost estimation of tunneling projects is usually performed in a deterministic manner. However, because the deterministic approach is not capable of dealing with uncertainty, probabilistic methods have been developed over the years to better account for this problem. Three models of this type are the Decision Aids for Tunneling (DAT) and two models developed at KTH Royal Institute of Technology and the Czech Technical University in Prague. To conduct a probabilistic time and cost estimation, it is important to understand and account for not only the uncertain factors that affect the project time and cost but also the involved parties’ different interests and contractual responsibilities. This paper develops a risk model for the specific purpose of time and cost estimation of tunneling projects. In light of this model, the practical application of the three probabilistic models is discussed from a risk-aware decision-maker’s perspective. The acquired insights can be helpful in increasing the experts’ risk-awareness in modeling time and cost of tunneling projects.

Cost estimation model of prefabricated construction for general contractors based on system dynamics

PurposeThe poor capacity of prefabricated construction cost estimation is the essential reason for the low profitability of the general contractor. Therefore, this study aims to focus on the cost estimation of prefabricated construction as the research object. This research aims to enhance the accuracy of total project cost estimation for general contractors, ultimately leading to improved profitability.Design/methodology/approachThis study used Vensim PLE software to establish a system dynamics model. In the modeling process, a systematic research review was used to identify cost-influencing factors; ABC classification and the analytic hierarchy process were used to score and determine the weights of influencing factors.FindingsThe total cost error obtained by the model is less than 2% compared with the actual value. It can be used to cost estimation and analysis. The analysis results indicate that there are 7 key factors, among which the prefabrication rate has the most significant impact. Furthermore, the model can provide the extreme range cost; the minimum cost can reduce by 13% from the value in the case. The factor's value can compose a cost control strategy for general contractors.Practical implicationsThe cost of prefabricated buildings can be estimated well, and deciding the prefabrication rate is crucial. The cost can be declined by correct cost control strategies when bidding and subcontracting are in process. The strategies can follow the direction of the model.Originality/valueA systemic, quantitative and qualitative analysis of cost estimation of prefabricated buildings for general contractors has been conducted. A mathematical model has been developed and validated to facilitate more effective cost-control measures.

Assessment of Cost and Time Performance of Tertiary Educational Trust Fund (TETFund) Construction Project in South-West Nigeria

Funds have been allocated to TETFund annually for infrastructural development in Nigeria to address decays of educational facilities and create an enabling environment for teaching and learning. This study evaluates time and cost performance of public building construction projects funded by TETFund in South-West Nigeria. The study adopted questionnaire survey by self-administering two hundred and fifty (250) questionnaires to project clients, consultants and contractors engaged in TETFund projects in South-West Nigeria. One hundred and eighty-six 186 (74.4%) of the questionnaires were retrieved from the respondents and were used in the study. Also, record of project cost and duration were purposively obtained from two hundred and fifty-four (254) TETFund sponsored projects from Institutions in South-West Nigeria. Mean Score (MS) was used to rank the various items and components while regression analysis was used to forecast future project cost and time. The top three factors that influence cost and time based on the perceptions of the respondents are client satisfaction with the project (MS= 3.86), construction time predictability (MS= 3.85) and construction cost predictability (MS= 3.83). From the TETFund project records analysed, a total sum of ₦10,856,167,497.14 was spent on TETFund building construction projects in South-West Nigeria from 2003-2013 with a contingency sum of ₦163,248,265.44. The average percentage cost overrun for TETFund projects was 1.62% and that of time overrun was 112.23%. Regression analysis of the predicted project time and cost was significant and can be used to forecast time and cost of future TETFund projects. Therefore, it was recommended that accurate cost estimate, adequate project planning and good specification should be carried out by project stakeholders before contracts are awarded to enhance construction project performance. Also, the developed regression model of estimated project cost and time can be used to predict cost and time of future construction projects.

DATA QUALITY ISSUES THAT HINDER THE IMPLEMENTATION OF ARTIFICIAL NEURAL NETWORK (ANN) FOR COST ESTIMATION OF CONSTRUCTION PROJECTS IN MALAYSIA

The Artificial Neural Network (ANN) which is one of the Artificial Intelligence (AI) tools, has been identified as a great technique to be used for construction cost estimation in the project. With the optimum quality of data input into the ANN model, it could produce an optimum and reliable cost estimation output. Nonetheless, the construction industry is lack of breadth and depth of data that is required as input into ANN. Though many online databases have been made available for data consumers, data quality problems remain unresolved. Thus, this study aims to identify data quality issues that can hinder the implementation of ANN for cost estimation of a construction project. A literature review and semi-structured interview were employed for the data collection of this research. The content analysis method was used to analyse the information obtained through the literature review. Meanwhile, the data collected from the semi-structured interview with nine (9) respondents were analysed using both content analysis and descriptive statistics analysis methods. The findings revealed six data quality issues that can hinder the ANN implementation for cost estimation of construction projects in Malaysia which are inaccurate data, outdated data, data access barriers, insufficient data, noise in training data, and data input degree of influence. Academically, this study contributes to the body of knowledge about the implementation of ANN for cost estimation of construction projects in Malaysia.
 
 Keywords: Artificial Neural Network, Artificial Intelligence, Cost Estimation, Data Quality.