Cost Estimation Model Research Articles

Risk-Based Completion Cost Overrun Ratio Estimation in Construction Projects Using Machine Learning Classification Algorithms: A Case Study

Estimating the completion cost accurately in the early phases of construction projects is critical to their success. However, cost overruns are almost inevitable due to the risks inherent in construction projects. Hence, the completion cost fluctuates throughout the execution phase and requires periodic updates. There is a need for a prompt and user-friendly completion cost estimation model that accounts for fluctuating risk scores and their impacts on the total cost during the execution phase. Machine learning (ML) techniques could address these requirements by providing effective methods for tackling dynamic systems. The proposed approach aims to predict the cost overrun ratio classes of the completion cost according to the changes in the total risk scores at any time of the project. Six classification algorithms were utilized and validated by employing 110 data points from a globally operating construction company. The performances of the algorithms were evaluated with validation and performance indices. The decision tree classifier surpassed other algorithms. Although there are some research limitations, including risk perception, data gathering restrictions, and selecting proper ML algorithms upon data properties, this research improves the planning abilities of construction executives by providing a cost overrun ratio based on changing total risk scores, facilitating swift and simple assessments at any stage of a construction project’s execution.

Net Present Value Calculations for Mining Post-Closure Financial Assurance

AbstractMost regulatory jurisdictions now require financial assurance for mines for post-closure activities, which typically include long-term monitoring and maintenance, and most importantly post-closure water treatment. Critical choices in calculating post-closure financial assurance include using a reputable cost estimation model to establish the amount needed for reclamation, selecting a realistic net return-on-investment for post-closure trust funds, and choosing the period of time over which the net present value calculation of the financial assurance is based. A conservative estimate of the amount of financial assurance is warranted to protect the public from assuming these costs. However, some regulatory agencies use financial assurance estimate practices that are arbitrary. The data and procedures needed to analyze and recommend conservative net present value calculations are readily available, but in too many instances are not being utilized.

Synthesis of activity-based costing and deep learning to support cost management: A case study in the automotive industry

Activity based costing (ABC) models for cost management and big data analytics are deeply rooted in academia and practice to efficiently manage operational costs. Inspired by cost management and deep learning (DL) theories we develop a multilayer perceptron (MLP) using a nested particle swarm optimized (PSO) neural network algorithm for self-controlled architecture and weight optimization. This innovative approach enables to mimic ABC while increasing prediction accuracy. In a real-world case study we use wheel manufacturing data provided by a large original equipment manufacturer (OEM) and follow a full factorial experimental design. Furthermore, we benchmark our novel DL approach with results derived from a traditional ABC analysis. We demonstrate that this intelligent cost estimation model can mimic ABC using few cost drivers contributing to efficient and transparent interorganizational cost management. Major quantitative findings within a conducted field experiment demonstrate a high forecast accuracy with low absolute cost percentage error (CPE) deviation of the novel cost estimation approach in industry. The results extend the scope of PSO for the simultaneous optimization of the architecture and weights of neural networks. Additionally, we prove that the PSO algorithm is a suitable alternative to traditional optimization methods in DL.

Formulation of train routing selection problem for different real-time traffic management objectives

The train routing selection problem (TRSP) addresses the optimized selection of alternative routes as a preliminary step for real-time railway traffic management problem (rtRTMP). In the TRSP, route selection relies on estimating potential delays resulting from scheduling decisions. The selected routes are then exclusively applied in the rtRTMP. While prior research established the mathematical model and solution algorithms for the TRSP, its practical application in real-time rail traffic management remains limited. The existing TRSP model focuses on a single objective function for the rtRTMP. However, in practice, various stakeholders may prioritize different objectives, leading to diverse objective functions employed in the rtRTMP. This paper extends the TRSP model by considering a range of suitable objectives for the rtRTMP. We formulate the TRSP for each objective function and enhance the cost estimation model to evaluate the correspondence between the TRSP and rtRTMP objective functions. We then assess the overall effectiveness of the TRSP for the rtRTMP through an evaluation that takes into account several configurations of the model and the rtRTMP solution approach used. Our purpose is to enlarge the applicability of the TRSP and enhance the efficiency of the rtRTMP for real-world systems. The paper includes an in-depth computational analysis of two French case studies to investigate the performance of the TRSP across different rtRTMP configurations.

Forecasting the software engineering model’s effort estimation using constructive cost estimation models

Forecasting the software engineering model’s effort estimation using constructive cost estimation models

Project Delay And Cost Overrun in Software Industry in the Kingdom of Saudi Arabia: The Powerful Role of GQM

Background: Given the enormous impact that the software industry has on so many facets of our lives today, software projects are extremely important. Digital transformation is driven across industries by software developments. They facilitate the utilisation of technology by organisations to optimise operations, augment productivity, and provide inventive products and services. To be competitive and adjust to the quickly changing market dynamics of today's world, companies must undergo digital transformation by making full use of software projects. Objectives: The main aim of the current study is to determine the main causes of project delay and cost overrun in software projects, identify the effects of project delay and cost overrun on software projects, and define the role of cost estimation models in overcoming project delays and cost overruns in these projects. Results and conclusions:The researcher reviews the literature on causes behind delay and cost overrun and describes the role that can be played by cost estimation models in that process. In light of the reviewed literature, the researcher reaches certain recommendations for the software industry.

Developing a cost estimation model for efficient road improvement planning: A case study in Aceh Jaya regency

Abstract Estimation is a method used to predict financial requirements by analyzing, calculating, and engineering based on field conditions and bidding documents. To enhance efficiency, there is a pressing need for a simple, swift, accurate cost estimation model. Therefore, this study aimed to establish cost estimation model at the initial planning phase of construction work and to assess its accuracy in estimating cost for road improvement using cost significant model (CSM) compared to actual expenses. The fundamental objective was to facilitate the execution of construction work, ensuring the successful completion. Data collection occurred at the (PUPR) in Aceh Jaya Regency, consisting of 25 contracts for road improvement work spanning from 2018 to 2022. The data included the execution year, road area, total variable cost (y), and the categorization of work item as independent variables (xn). Subsequently, the work data was transformed into data per square meter (m2) for each work item by dividing each independent variable by the area of road improvement work. This showed the cost/m2 for each work item (xn) and the total cost (y)/m2. Annual inflation data was obtained from (BPS) of Aceh province used for calculation projection year. The identification of cost-significant item variables occurred after organizing the data according to work item, adjusting the work cost for the execution year and the work-year cost while considering inflation factor. Additionally, it was observed that 3 most expensive work items represented 80% work item had a substantial impact on the total cost. Classic assumption tests were conducted to confirm the suitability of data for further analysis. The analysis was conducted using multiple linear regression, resulting in a model with y = 69850.515 + 0.879(x4) + 1.085(x5) + 1.221(x7). When cost significant model estimates were compared to the actual total cost of road improvement in Aceh Jaya, the accuracy ranged from +17.46% to -19.30%, which was consistent with Class 3 classification of (AACE) International standards.This classification was suitable for semi-detailed cost estimation in the conceptual phase.

ABC model for cost estimation of custom implants by Additive Manufacturing.

Computer-aided design (CAD) models can now be directly converted into products and structures. One technique to realize such approach is through Additive Manufacturing (AM). AM is relatively new manufacturing technology in which products are manufactured by layering various materials like rubber, metal, ceramic, composites, and polymers. However, the use of this technology requires consideration of its associated cost to ensure its competitiveness. In this paper, a simplified mathematical cost model is suggested. The model considers the main components of costs. The model formula utilizes expenses related to the pre-processing, main processing, and the post-processing operations. To validate the model, it is tested to estimate the cost of medical implants manufacturing using AM technique. In many cases, medical implants require unique or dedicated design for each patient. Hence cost estimation will help to assess and estimate the required financial resources for such operations. A case study is provided in this paper to estimate the manufacturing cost of a finger's phalanges bone, with metal implant using AM technique. The developed model may be described as Activity Based Costing (ABC). The model is introduced to estimate the cost of parts produced using AM technique. Although the model is developed to suit custom implant manufacturing using AM technique, its use may also be adapted to suit the manufacturing of many other parts and products. The developed model is aiming to achieve several tasks namely assigning cost drivers to each activity, estimating the cost of individual actions, allocating overhead expenses, calculating the overall production cost, and establishing an acceptable selling price. It assists companies in computing the cost of custom implants for customers, enhancing the accuracy of production cost estimates, and ultimately boosting profitability.

Modeling Cost-Estimation Factors for Public Building Projects with Hybrid Approach in Addis Ababa

Assessing the most important cost-influencing factors is essential for enhancing the predictive ability of cost estimation for building construction projects. The goal of this study is to examine and design a valid cost prediction model for assessing factors that impact the cost estimation of public buildings in Addis Ababa. This research solves these issues that typically arise in predictive cost estimation models in two major processes. First, the insights of 133 professionals gathered on the 38 cost-impacting elements, and 15 top factors design, time or cost, and parties’ experience were determined. The suggested hybrid approach is based on the Akaike information criterion (AIC) and principal component regression (PCR) employed, coupling a stepwise linear regression model. According to the findings of the study, principal component analysis reduced important factors to 14 and efficiently solved the problem of multicollinearity with a variance inflation factor of less than 2, while stepwise cross-validation solved the overfitting problem at the lowest AIC. The cost prediction model sorted out five factors: design completion by the public body when bids are invited; completion of the project scope definition when bids are invited; level of construction complexity; importance of project completion within budget; and subcontractor experience and capability have all been identified as the main cost-determining factors. The study’s contribution is the first approach (PCR–AIC) utilized in this work to explore numerous cost-estimating components, eliminate those that were related to one another, and identify the most crucial ones that consisted of the majority of the original variables’ attributes.

Strategies of Public University Building Maintenance—A Literature Survey

In this article, comprehensive insights into the field of building maintenance, emphasizing the importance of keywords, collaborative efforts among authors, and the evolving research landscape, are provided. The use stage, as the longest phase in a building’s life cycle, involves economic, technical, and social activities. Numerous authors have contributed to the broader topic of building maintenance, covering aspects such as maintenance prioritization, improvement actions, decision-making guidelines, factors affecting success, cost estimation models, and BIM usage in maintenance. The study conducts a thorough literature review using Scopus as a search engine, employing the full-counting method for authorship, and uses VOSviewer 1.6.20 software for bibliometric analysis to identify gaps and outline future research directions. The results reveal distinct data sets focusing on building maintenance from general to specific, with each set reflecting unique aspects and considerations. Bibliometric maps illustrate author collaboration and keyword connections within each set, highlighting evolving research trends and areas of focus. Overall, the analysis highlights the importance of prioritizing maintenance, integrating technology, and fostering collaboration to enhance building maintenance in educational institutions. The study concludes with recommendations for future research, emphasizing the ongoing need for exploration and development in building maintenance, especially on maintenance strategies and Life Cycle Costs of university buildings.

Developing preliminary cost estimates for foundation systems of high-rise buildings

This study provided a unique Artificial intelligence (AI) model for the cost estimation of the foundation system for high-rise buildings. First, parametric data research was conducted, including 180 examples of foundation systems for high-rise building models related to criteria such as average column spacing, floor height, slap load, overall weight, base shear, and over. In addition, moment, gravity load, seismic load, design load, various columns (mid-edge-corner), soil profile, bearing capacity, GWT, excavation depth, and foundation systems are all factors to consider (shallow and deep footing). The research encompassed column spacing (5.0, 7.0, and 9.0 m) and the number of stories from 15 to 35, with an average cost decrease of 15%. The AI model utilizes extensive machine learning algorithms to analyze structural and geotechnical parameters. It provides a predictive tool that improves decision-making in the preliminary design. The methodology includes collecting data, training models utilizing innovative neural network techniques and validating them against current cost estimation models. The findings indicate that the AI model significantly improves the accuracy of cost estimations, with a precision rate of 95%, compared to traditional methods. Moreover, the model presents a potential cost savings of up to 15%. Construction designers and decision-makers may utilize the study’s findings to increase the accuracy of foundation system selection, lower costs and construction length, and improve overall project performance. Future work may involve applying this concept to infrastructure and substructure projects and collecting more data for benchmarking and empirical study.

Main cost estimation models in projects used by banks and fintechs in Brazil

Main cost estimation models in projects used by banks and fintechs in Brazil

A conceptual cost estimation model for the pre-design stage of road projects using multiple regression analysis

PurposeThe current estimation practice in construction projects greatly needs upgrading, as there has been no improvement in the cost overrun issue over the past 70 years. The purpose of this research was to develop a new multiple regression analysis (MRA)-based model to forecast the final cost of road projects at the pre-design stage using data from 43 projects in New Zealand (NZ).Design/methodology/approachThe research used the case study of 43 completed road projects in NZ. Document analysis was conducted to collect data, and statistical tests were used for model development and analysis.FindingsEight models were developed, and all models achieved the required F statistics and met the regression assumptions. The models’ mean absolute percentage error (MAPE) was between 21.25% and 22.77%. The model with the lowest MAPE comprised the road length and width, number of bridges, pavement area, cut and fill area, preliminary cost and cost indices change.Research limitations/implicationsThe model is based on road projects in NZ. However, it was designed to be able to adapt to other contexts. The findings suggest that the model can be used to improve traditional conceptual estimating methods. Past project data is often stored by the project team but rarely used for analysing and forecasting purposes. This research emphasises that past data can be effectively used to predict the project cost at the pre-design stage with limited information.Originality/valueNo research was conducted to adopt cost modelling techniques into the conceptual estimation practice in the NZ construction industry.

Dimensionality reduction and machine learning based model of software cost estimation

Software Cost Estimation (SCE) is one of the research priorities and challenges in the construction of cyber-physical-social systems (CPSSs). In CPSS, it is urge to process environmental and social information accurately and use it to guide social practice. Thus, in response to the problems of low prediction accuracy, poor robustness, and poor interpretability in SCE, this paper proposes a SCE model based on Autoencoder and Random Forest. First, preprocess the project data, remove outliers, and build regression trees to fill in missing attributes in the data. Second, construct a Autoencoder to reduce the dimensionality of factors that affect software cost. Subsequently, the performance of the model was trained and validated using the XGBoost framework on three datasets: COCOMO81, Albrecht, and Desharnais, and compared with common cost prediction models. The experimental results show that the MMRE, MdMRE, and PRED (0.25) values of the proposed model on the COCOMO81 dataset reached 0.21, 0.16, and 0.71, respectively. Compared with other models, the proposed model achieved significant improvements in accuracy and robustness.

A New Approach for Software Cost Estimation with a Hybrid Tabu Search and Invasive Weed Optimization Algorithms

Due to the ever-increasing progress of software projects and their widespread impact on all industries, models must be designed and implemented to analyze and estimate costs and time. Until now, most of the software cost estimation (SCE) has been based on the analyst’s experiences and similar projects and these models are often inaccurate and inappropriate. The project will not be finished in the specified time and will include additional costs. Algorithmic models such as COCOMO are not very accurate in SCE. They are linear and the appropriate value for effort factors is not considered. On the other hand, artificial intelligence models have made significant progress in the cost estimation modeling of software projects in the past three decades. These models determine the correct value for effort factors through iteration and training, providing a more accurate estimate compared to algorithmic models. This paper employs a hybrid model incorporating the Tabu Search (TS) algorithm and the Invasive Weed Optimization (IWO) algorithm for SCE. IWO algorithm solutions are improved using the TS algorithm. The NASA60, NASA63, NASA93, KEMERER, and MAXWELL datasets are used for the evaluation. The proposed model has been able to reduce the MMRE rate compared to the IWO algorithm and the TS algorithm. The proposed model on the NASA60, NASA63, NASA93, KEMERER, and MAXWELL datasets obtained values of MMRE of 15.43, 17.05, 28.75, 58.43, and 22.46, respectively.

Evaluating urban mini plant factories: engineering and software cost perspectives for agriculture sustainability

Precision agriculture serves as a crucial solution to address the challenges of food security and agriculture sustainability. It provides significant benefits and enables effective monitoring of agriculture throughout the entire supply chain using a technology-driven approach that prioritizes internet connectivity and leverages big data. A noteworthy application of precision agriculture is the Mini Plant Factory, where plants are cultivated in closed systems with artificial lighting. The development of the Mini Plant Factory requires an economic feasibility analysis as a determinant of technology viability before widespread implementation, aiming to promote agriculture sustainability. The Software Cost Estimation Model (SCEM) assesses software development’s cost and time requirements. Engineering economics evaluates economic feasibility using metrics like NPV, BCR, IRR, PBP, and BEP methods. Function Point Analysis for UMPF software development estimates a cost of Rp 33,052,414, equivalent to 1,311 man-hours. Investment feasibility analysis considers the utilization of UMPF as viable, with an NPV of IDR 46,938,615, BCR of 1.08, IRR of 28%, and projected profitability within four years. Precision agriculture strategically addresses complex agricultural challenges, fostering sustainability with innovations such as the UMPF. The SCEM and engineering economics confirm the feasibility and rationale for implementing UMPF technology, providing essential insights for sustainable agricultural practices.

Fuzzy activity-based costing: An investment evaluation approach for management information system of a smart factory

The investment in a smart manufacturing factory with corresponding management information systems is strategic, complex, and costly. This paper aims to develop a cost estimation framework for a smart factory management information system (SFMIS). This paper proposed a fuzzy activity-based costing (FABC) model for the evaluation of the SFMIS under conditions of uncertainty. The model presented a multi-step procedure to do the identification, estimation, determination, calculation, and computation of the resource costs, activity costs, and systems as cost objects. The fuzzy Delphi method is adopted, and seventeen experts are surveyed in two rounds of a questionnaire assessing the importance of resources, activities, systems, and industry type and company size. The proposed FABC cost estimation model is illustrated by a case study. This model can identify and allocate resources and estimate SFMIS costs accurately and efficiently. By using this FABC cost evaluation framework, policymakers facilitate smart factory implementation for its management information system under uncertainty.

The selection parameter for the operation and maintenance dam based on activity-based costing

Potential risks to people exist if a dam collapses and has a significant impact on the downstream area. Many countries are now facing the problem of having to deal with deteriorated infrastructure due to a lack of maintenance budgeting. This paper presents the dominant parameter in an Operational and Maintenance (OM) dam to build a cost estimation model to maintain the service life of the dam. The method used to identify cost-triggering parameters is based on activity-based costing and dam performance assessments using a combination of the modified Andersen, International Commission of Large Dams (ICOLD), and Dam Commission. The parameter was collected from fourteen independent variables, namely: dam height, irrigation area, sedimentation volume, grass area, wood vegetation area, corrosion area, concrete area, daily worker, corrosion expert, concrete deterioration, hydromechanical, physical performance, operation performance, and safety performance. The results of the model indicate that height, wood vegetation area, concrete maintenance area, hydromechanical deterioration, and safety performance are variables that affect OM costs. The OM costs can be reduced if the safety performance variable increases. This condition implies that if the safety performance component consists of dam monitoring activities, periodic inspections, green belt maintenance, water quality maintenance, and public awareness, the OM costs will decrease by 10%.

Improvement of Risk Management in Cost Estimation in the Building Construction Industry in Uganda

The cost performance of construction projects is a crucial success factor. However, risks in construction projects make exact budgetary requirements challenging to forecast accurately, resulting in underestimation and overestimation. Inaccurate cost estimates could further result in unnecessary financial loss to project stakeholders and the loss of reputation and trustworthiness of construction professionals. In Uganda, risk factors are either ignored or subjectively taken care of by simply allowing a contingency figure ranging from 0% to 10% of the project cost. However, this method is sometimes unreliable and difficult to justify to project owners. Therefore, there is a need for a reliable and justifiable risk-based cost estimation method. The current study aimed to improve risk management in cost estimation in the building construction industry in Uganda. The specific objectives were to establish the risk factors, assess the effects of the risk factors and develop a reliable model that can be used for risk-based cost estimation in the building construction industry in Uganda. The study adopted a mixed-method approach by utilising quantitative and qualitative research methods. The collection of data was done using a self-administered questionnaire and an interview guide. The data was first sorted, coded and entered for analysis using the Statistical Package for the Social Sciences (SPSS) and Microsoft Excel. The risk factors in cost estimation were identified through a detailed literature review. The study revealed that the top five risk factors influencing cost estimation were: cost of materials, inflation, fraudulent practices and kickbacks, incomplete scope definition, and incomplete design and specification. The study concluded that the risk factors with the most severe effects on cost estimation were inflation, proficiency in estimating, cost of materials, incomplete design and specification, fraudulent practices and kickbacks. The study proposed a model developed using the analytic hierarchy process (AHP). The study recommends more research on the efficiency and effectiveness of risk-based cost estimation models.

Evaluating Smart Greenhouse Viability Through Engineering Design and Software Cost Modelling

Introducing smart greenhouse technology in tropical agricultural in Indonesia has the potential to bring about substantial advantages, such as higher crop yields, decreased water consumption, and enhanced food security. Nevertheless, the feasibility of this technology must be evaluated before it can be widely adopted. The objectives of this study were to evaluate the viability of smart greenhouse technology in using the engineering economics and software cost estimation model (SCEM), consider the fixed and variable cost for operational, and effort for developing the supporting modules. The findings of this study suggest that the investment in Smart Greenhouse technology is economically viable and financially justified. The Internal Rate of Return (IRR) of 11% exceeds the 10% discount rate, Benefit Cost Ratio (BCR) of 1.16 signifies that the discounted value of benefits surpasses costs over the project lifetime, with the economics return 16% higher than the break-even level. The Smart Greenhouse investment will become profitable after five years, with positive returns above the minimum threshold. The SCEM analysis shows that the software development workload is significant for some modules, such as Smart Agri Engrow and Smart Agri Nutrigrow. These software cost estimates can now be used for budgeting, planning, and assessing the feasibility of the Smart Greenhouse technology implementation.