Cost Forecasting Research Articles

Intelligent Forecast Model for Project Cost in Guangdong Province Based on GA-BP Neural Network

Project cost forecasting is a complex and critical process, and it is of paramount importance for the successful implementation of engineering projects. Accurately forecasting project costs can help project managers and relevant decision-makers make informed decisions, thereby avoiding unnecessary cost overruns and time delays. Furthermore, accurately forecasting project costs can make important contributions to better controlling engineering costs, optimizing resource allocation, and reducing project risks. To establish a high-precision cost forecasting model for construction projects in Guangdong Province, based on case data of construction projects in Guangdong Province, this paper first uses the Analytic Hierarchy Process (AHP) to obtain the characteristic parameters that affect project costs. Then, a neural network training and testing dataset is constructed, and a genetic algorithm (GA) is used to optimize the initial weights and biases of the neural network. The GA-BP neural network is used to establish a cost forecasting model for construction projects in Guangdong Province. Finally, by using parameter sensitivity analysis theory, the importance of the characteristic values that affect the project cost is ranked, and the optimal direction for controlling the project cost is obtained. The results showed: (1) The determination coefficient between the forecasting and actual values of the project cost forecasting model based on the BP neural network testing set is 0.87. After GA optimization, the determination coefficient between the forecasting and actual values of the GA-BP neural network testing set is 0.94. The accuracy of the intelligent forecast model for construction project cost in Guangdong Province has been significantly improved after optimization through GA. (2) Based on sensitivity analysis of neural network parameters, the most significant factor affecting the cost of construction projects in Guangdong Province is the number of above-ground floors, followed by the main structure type, foundation structure, above-ground building area, total building area, underground building area, fortification intensity, and building height. The results of parameter sensitivity analysis indicate the direction for cost control in construction projects. The research results of this paper provide theoretical guidance for cost control in construction projects.

УДОСКОНАЛЕННЯ ОРГАНІЗАЦІЙНОГО ЗАБЕЗПЕЧЕННЯ ПРОЦЕСУ ЗАЛУЧЕННЯ ФОРМИ ВЕНЧУРНОГО БІЗНЕСУ ДЛЯ РОЗВИТКУ ПІДПРИЄМСТВА В УМОВАХ ЦИФРОВІЗАЦІЇ ЕКОНОМІКИ

The necessity for improving the existing organizational framework for engaging venture business forms is justified, aiming to facilitate the implementation of new technologies, elevate production to a higher level, and enhance the competitiveness of enterprises in both domestic and international markets. The organizational support for involving venture business forms in the development of industrial enterprises in the conditions of economic digitization is enhanced. A scheme for selecting the organizational form of venture business and funding sources is proposed, allowing the utilization of digital transformation tools to increase the effectiveness of venture business engagement. Venture business is defined as entrepreneurial activity involving the infusion of risky investments into the innovative development of a knowledge-intensive industry, prone to potential growth. The following organizational forms of venture business are identified: "independent ventures," "external ventures," and "internal ventures". Various types of organizational forms of venture business and sources of their funding are considered. The engagement of venture business forms is carried out through financing the venture using various capital sources, specifically from the company's cash fund, funds from venture investors, and funds obtained from a venture fund. Using the PATTERN method, a goal tree for each form of venture business and funding source is constructed. The cost forecast for organizing an internal venture with funding from the company's own financial resources is conducted. The author also proposed an alternative venture financing option using the company's funds, such as raising funds from a venture fund through the sale of 10–20% of the company's shares. The proposed measures will enable industrial enterprises to overcome their crisis and become competitive in both external and internal markets.

Development of a Prediction Model for Construction Project Cost in India: an Analytical Approach A Review

The fundamental problem in the construction industry is that building projects are completed attaken a tolls significantly higher than estimated venture taken a tolls consequently, it is fundamental todevelop a taken a toll forecast show that detain all components influencing the extend taken a toll bymeans of relapse examination. Development costs are continuously inclined to vacillations, with a longtermdesign of expanding, making the estimating prepare a difficult errand. Vacillations within the fetchedof building materials have a noteworthy affect on foreseeing the esteem of a venture and, as a result, onthe project's great conclusion It is well known that civil engineering projects are prone to cost overrunsand schedule delays. Lack of project scope and frequent changes leads to a negotiation process interms of cost and time between the first partyowner and the second partycontractors. In the project lifecycle, cost forecast is a precursor to budget prices and resource allocation, thus it is critical for anyorganization. The following objectives are framed based on the literature study identify the constructioncost predictability of various tools, identify the various influencing factors to predict the material price ofcement and steel, model the Construction Cost Index (CCI), predict the construction duration (Especiallyfor highway projects, as compared to other kind of projects. They are having more obstacles to completethe task), predict the land value, Regarding this issue this paper find the best methodology for thePrediction Model for Construction Project Cost by analysising the different researchers papersresearch.

Energy cost forecasting and financial strategy optimization in smart grids via ensemble algorithm

Energy cost forecasting and financial strategy optimization in smart grids via ensemble algorithm

High-Voltage, Long Term-Stable and Wearable Zinc-Ion Hybrid Batteries with Gel Biopolymer Electrolytes

We are on the eve of the energy transition towards the phase-out of coal, electromobility and renewable power supply. Lithium-ion batteries (LIBs) and electric double-layer capacitors (EDLCs) are complementary energy storage devices supporting this technological change. They have dominated the commercial market of power sources, serving as energy supplies for various technologies ranging from daily electronics and gadgets through electric vehicles to management systems of the intermittent electric grid. However, conventional energy storage systems present some challenges regarding operational safety, the expected increase in production costs, the risk of limited availability of raw natural resources, and universal waste disposal.1,2 Zinc-ion rechargeable power sources, including batteries and hybrid supercapacitors, are a promising alternative to commercial LIBs and EDLCs.3,4 This technology integrates attractive features, such as high gravimetric and volumetric theoretical capacity, low cost, high safety, and environmental friendliness. Nevertheless, the widespread adoption of zinc-ion systems for powering commercial devices still faces challenges related to electrode design, the risk of liquid electrolyte leakage, rigid construction, and the presence of synthetic polymer-based components. This research attempts to address the aforementioned shortcomings by exploring the concept of biopolymer-based zinc-ion systems.Herein, we present zinc-ion hybrid batteries employing gel biopolymer electrolytes. Batteries and dual-ion hybrid batteries of aqueous Zn-ion technology operate according to similar mechanisms, differing on the catholyte side. In Zn-ion batteries, zinc ions are involved in the reactions on both electrodes, whereas hybrid systems have cathodes adopted from alkaline metal-ion technologies, operating according to intercalation/deintercalation processes of monovalent cations, e.g., Li-ion, Na-ion, K-ion, etc.5 As observed, hybrid devices are feasible with fast kinetics, good stability, and flat and high discharge voltage plateau. The application of gel electrolytes additionally improves their performance on the anode side, facilitating Zn stripping/plating processes due to homogeneous current distribution and flat Zn deposition. Generally, the presented idea emerges as a promising strategy, offering an efficient, safe, low-cost, non-combustive, flexible and sustainable technology. Particular attention is paid to overcoming LIB performance and environmental limitations whilst developing wearable features through innovative biobased technological improvements.References(1) Mauler, L.; Duffner, F.; Zeier, W. G.; Leker, J. Battery Cost Forecasting: A Review of Methods and Results with an Outlook to 2050. Energy Environ. Sci. 2021, 14 (9), 4712–4739.(2) Simon, P.; Gogotsi, Y.; Dunn, B. Where Do Batteries End and Supercapacitors Begin? Science (80-. ). 2014, 343, 1210–1211.(3) Wang, Y.; Sun, S.; Wu, X.; Liang, H.; Zhang, W. Status and Opportunities of Zinc Ion Hybrid Capacitors: Focus on Carbon Materials, Current Collectors, and Separators. Nano-Micro Lett. 2023, 15 (1), 78.(4) Tang, B.; Shan, L.; Liang, S.; Zhou, J. Issues and Opportunities Facing Aqueous Zinc-Ion Batteries. Energy Environ. Sci. 2019, 12 (11), 3288–3304.(5) Shi, Y.; Chen, Y.; Shi, L.; Wang, K.; Wang, B.; Li, L.; Ma, Y.; Li, Y.; Sun, Z.; Ali, W.; Ding, S. An Overview and Future Perspectives of Rechargeable Zinc Batteries. Small 2020, 16 (23), 2000730. Figure 1. Work concept. Figure 1

Operational optimisation of a microgrid using non-stationary hybrid switched model predictive control with virtual storage-based demand management

Demand-shaping mechanisms are a key component of modern energy management systems, although not unproblematic. The degree of social acceptance of interference with demand or generation and the ease of integration of various types of non-critical loads depends on the method of their implementation. In addition, the critical load pool typically includes devices with different response times. The energy management systems currently in use often cannot meet user expectations. Especially when considering other vital aspects, such as energy market spread, storage wear, or connection to the utility grid and neighbouring microgrids. The authors adopted an approach of unifying demand side management and response in the form of virtual energy storage. Said store allows for the accommodation of loads operating under differing scheduling horizons. Such a new concept allows management not only in terms of quantity but also in terms of time. The storage is the focal point of a comprehensive energy management system based on switched model predictive control. The receding horizon algorithm relies on a non-stationary hybrid microgrid model. The study compares the operating costs of microgrids with virtual storage, allowing only demand postponement, preponement or bidirectional operation. The energy management system is also examined for sensitivity to changes in the weight matrices of the cost function, horizon length and forecast inaccuracy. Introducing virtual energy storage reduces microgrid operating costs by up to 16%. The decrease in control performance is proportional to the prediction accuracy, and the sensitivity allows for customisation.

Bridging operations research and machine learning for service cost prediction in logistics and service industries

AbstractOptimizing shared resources across multiple clients is a complex challenge in the production, logistics, and service sectors. This study addresses the underexplored area of forecasting service costs for non-cooperative clients, which is essential for sustainable business management. We propose a framework that merges Operations Research (OR) and Machine Learning (ML) to fill this gap. It begins by applying the OR model to historical instances, optimizing resource allocation, and determining equitable service cost allocations for each client. These allocations serve as training targets for ML models, which are trained using a combination of original and augmented client data, aiming to reliably project service costs and support competitive, sustainable pricing strategies. The framework’s efficacy is demonstrated in a reverse logistics case study, benchmarked against two traditional cost estimation methods for new clients. Comparative analysis shows that our framework outperforms these methods in terms of predictive accuracy, highlighting its superior effectiveness. The integration of OR and ML offers a significant decision-support mechanism, improving sustainable business strategies across sectors. Our framework provides a scalable solution for cost forecasting and resource optimization, marking progress toward a circular, sustainable economy by accurately estimating costs and promoting efficient operations.

Sustainability through the use of Building Information Modelling in infrastructure planning

This study examines the role of Building Information Modelling (BIM) in infrastructure planning from a sustainability perspective. It emphasises how BIM can contribute to the promotion of ecological, economic and social sustainability. Interviews with experts have shown that BIM can not only optimise the energy consumption of infrastructure projects, but also lead to precise material quantification and optimisation. Despite the benefits, the use of BIM in infrastructure planning is limited, especially in small and medium-sized projects and with local authorities. The study identifies challenges such as the complexity of BIM software systems and the additional costs of implementing them. Recommendations for action include training clients and engineering firms in the use of BIM for cost forecasting and extending the digital twin concept beyond the construction and planning process. The results show that widespread BIM application is only possible if both clients and planning offices share sustainability goals and are prepared to bear the additional costs for BIM planning. The work emphasises the need to use BIM beyond building construction for sustainable infrastructure development and provides insights into the practice of engineering firms in the infrastructure sector.

Sun Stats: An IoT Node MCU Integrated Web Application with Real-Time Energy Monitoring and Cost Forecasting

Rising global concerns about energy consumption and its environmental impact have fueled interest in renewable and sustainable energy sources, with solar energy emerging as a promising solution. In response to climate change challenges and the depletion of finite fossil fuel resources, there is a pressing need for innovative energy management solutions. This paper introduces "SunStats," an IoT NodeMCU integrated web application designed for real-time energy monitoring and cost (consumption) forecasting.
 SunStats combines weather data and cost forecasting to provide tailored capabilities for local residential users. Integrating smart technologies and data-driven approaches, it aims to empower consumers with valuable insights into their energy consumption patterns.
 It has a real-time energy monitoring feature, facilitated by the use of NodeMCU, allowing users to continuously track their energy consumption patterns. The user-friendly interface enables consumers to access real-time data on their electricity usage, facilitating informed decisions about energy management. Additionally, the application's integration of weather data offers contextual insights into how weather conditions influence energy usage, empowering users to adjust their consumption behavior accordingly.
 Beyond real-time energy monitoring and weather integration, SunStats incorporates cost forecasting. Utilizing historical energy usage patterns and weather data, the application predicts future energy consumption for users. This forecasting feature provides consumers with valuable information about potential fluctuations in energy consumption, enabling effective planning and informed decision-making.
 The primary goal of SunStats is to empower users to become proactive energy managers, offering transparency into real-time energy data, weather insights, and cost forecasts. This knowledge enables users to implement energy-saving strategies, optimize efficiency, and contribute to a more sustainable future.

Impact of unexpected conditions on construction cost forecasting performance: evidence from Europe

In order to prepare proper budgets, practitioners endeavor to forecast future cost fluctuations. In recent years, the COVID-19 pandemic and the Russia-Ukraine war have caused cost overruns in most construction projects, and there has been no effort to analyze the effects of such situations on cost forecasting performances. This paper aims to investigate the impact of unexpected conditions, such as pandemics and wars, on the construction cost forecasting performances of widely used univariate time series models. For this purpose, statistical forecasting models and two widely used machine learning techniques are employed for the construction cost forecasting of nine European economies in two scenarios: a stable period (2017–2020) and a fluctuating period (2020–2023). The results showed that the success of the models varied by region and period. Unexpected global conditions cause significant errors, especially in the medium and long term. There are significant increases in forecast errors between stable and fluctuating periods. This study provides comprehensive experimental results to determine the cost-forecasting risks of construction projects under unexpected global conditions. The investigation is limited to the European economies, which are mostly developed countries with low inflation rates. Therefore, the results should also be validated in underdeveloped and developing countries.

Project cost forecasting based on earned value management and Markov chain

Project cost forecasting based on earned value management and Markov chain

Improving Project Estimates at Completion through Progress-Based Performance Factors

From a managerial perspective, project success hinges on estimates at completion as they allow tailoring response actions to cost and schedule overruns. While the literature is moving towards sophisticated approaches, standard methodologies, such as Earned-Value Management (EVM) and Earned Schedule (ES), are barely implemented in certain contexts. Therefore, it is necessary to improve performance forecasting without increasing its difficulty. The objective of this study was twofold. First, to guide modeling and implementing project progress within cost and to schedule Performance Factors (PFs). Second, to test several PFs utilized within EVM and ES formulae to forecast project cost and duration at completion. Progress indicators dynamically adjust the evaluation approach, shifting from neutral to conservative as the project progresses, either physically or temporally. This study compared the performance of the progress-based PFs against EVM and ES standard, combined, and average-based PFs on a dataset of 65 real construction projects, in both cost and duration forecasting. The results show that progress-based PFs provide more accurate, precise, and timely forecasts than other PFs. This study allows practitioners to select one or more of the proposed PFs, or even to develop one, following the guidelines provided, to reflect best their assumptions about the future course of project performance.

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.

ANALYSIS OF COST AND TIME PERFORMANCE IN THE WADUNGASRI MARKET CHANNEL NORMALIZATION WORK IN SIDOARJO USING THE EARNED VALUE METHOD

The construction project management for Wadungasri Sidoarjo Market Drainage Normalization aims to achieve cost, quality, and time objectives within a 100-day timeframe. This study addresses a 7.44% delay experienced by contractors, seeking to establish early warning mechanisms for poor project performance. The Earned Value Method is employed, integrating time and cost value concepts. Key indicators such as Cost Variance (CV), Schedule Variance (SV), work productivity index (CPI), time productivity index (SPI), project completion cost forecast (EAC), and project completion schedule forecast (ECD) are utilized. The results reveal a required cost of Rp 563,044,547.85 (ETC) and a 65-day timeframe (ETS) at the end of the 7th week, with a 0.64% increase in project completion cost (EAC) over the contract cost. The project completion time (EAS) is estimated at 114 days, reflecting a 0.14% extension. The analysis emphasizes the importance for construction service providers to implement efficient methods and consistent supervision to avoid delays in the Wadungasri Sidoarjo Market Drainage Normalization project.

A hybrid forecasting model to predict the duration and cost performance of projects with Bayesian Networks

This paper presents a new hybrid forecasting model to predict the final time and cost of a project using input parameters from the project scheduling and risk analysis literature. The hybrid method integrates two well-known risk models. A Structural Equation Modeling constructs and validates a theoretical risk model to represent known relations between project indicators and the project performance. A Bayesian Networks is used to train the theoretical model using artificial project data from the literature. These two integrated models are then used to predict the final duration and cost of a new unseen project.The accuracy of this integrated model is compared with other well-known forecasting methods from the literature. The computational experiments on a set of 33 empirical projects show that risk models demonstrate a noteworthy advantage for time and cost forecasting. To show the usefulness of this method, it is compared with a set of known machine learning forecasting algorithms.These static predictions of risk models are also compared with some well-known dynamic forecasting methods that continuously update the time/cost predictions along the project progress. These dynamic models make use of predictors from the earned value management and earned duration management literature. The results show that the static risk models offer more precise forecasts than the dynamic methods in the first half of the project progress for time forecasting, but then loose their power in favor of the dynamic forecasts.

Construction and Application of Cost Prediction Model Based on Multiple Linear Regression Analysis

Production cost forecasting is the key link to control the production cost of products, is an important step for enterprises to scientifically plan the future cost level and cost objectives, and is also the basis for enterprises to make scientific decisions. Taking women's clothing as an example, this paper introduces a simple and practical product production cost prediction method based on multiple linear regression mathematical model, describes the establishment process and prediction steps of multiple linear regression mathematical model in detail, and makes a prediction empirical research. It is found that the design difficulty and production volume are the key factors affecting the production cost of women's clothing, while the unit cost of raw materials and the man-hour required for production are not significant. The sample equation was fitted by the least square method, and the mathematical model was established, and the empirical analysis was carried out by SPSS22.0 software. The results show that the model has a high degree of fitting and forecasting ability, and provides a scientific and practical cost forecasting tool for enterprises.

Enrolment Progression Trends of Grade 1 2017 CBC Cohort into Senior Secondary Schools in 2026 in Kenya.

Enrolment projections are critical for the government and planners to allocate education-related resources and ensure necessary school infrastructure and teachers are provided. In view of the new education system of 2-6-3-3-3 that was launched in 2017 in Kenya and named Competency Based Curriculum (CBC), there was need to come up with a projection of enrolment trends of Grade 1 2017 CBC cohort into Senior Secondary Schools in 2026. The objectives of the study were to project the enrolment progression trends of Grade 1 2017 CBC cohort into Senior Secondary Schools in 2026. This study was guided by the rational comprehensive (Synoptic) planning theory propounded by Faludi and Needham (1993), which allows for the evaluation that consists of procedures such as cost benefit analysis, systems analysis, and forecasting (projection) research. The study adopted a descriptive survey research design. All the primary and secondary schools in Kenya were the target population for the study. Collection of data was done by means of questionnaires, document analysis and direct observation. The study followed Thonstad’s Grade Transition Model for projecting the CBC enrolment trends of the 2017 Grade one cohort to Junior and eventually Senior School. The study considered 2017 to 2021 enrolment data. The findings of this study indicated an increase in CBC enrolment over the years to 2026. The study also established that an increase in enrolment leads to an increase of teacher requirement, physical infrastructure, and average school size. The study concluded that there will be a shortage of teachers and selected projected infrastructure due to the projected increase in enrolment at Senior secondary levels by 2026. The study therefore recommended the need to expand the physical infrastructure, the need for TSC to roll out a plan to employ more teachers by 2028. With the findings of this study, the MOE, and TSC may be guided to consider adequate and effective teacher training programmes for the teachers to be CBC compliant and the need for adequate textbooks supply in time for use during instruction. With the enrolment projections at Senior Secondary Schools in 2026, budgetary allocations will be much easier by the stake holders. Findings of this study would also inform policy makers including TSC and Ministry of Education to come up with practical policy reforms that would enhance provision of quality education in Vihiga County. This study can also guide Tertiary and University institutions for proper preparation when the learners graduate from Senior School.

Demand and Equilibrium Price of Health Care: A Structural Equation Approach

Abstract In this article, we propose a new approach to estimating health-care demand. The aim of this paper is to determine the production costs of health care from the demand function of care. To do this, we used an approach based on structural equations where consumption and demand are estimated to capture the dynamics of health costs within a self-managed public hospital. Following this approach, based on the equilibrium between supply and demand of health care, we used the social and professional characteristics of beneficiary to estimate the demand function, which will approximate the cost of health care. The results showed that the demand for care is largely dependent on economic, demographic, and perception factors. Also, the back testing and corroboration tests of the predictions affirm that the functions developed will allow a better cost forecast for the hospital unit, able to propose a budgetary and partial cost approach in the future. Some limitations can be mentioned in connection with the accessibility to accounting data and also the ignorance of time dimension or dynamic evolution of cost demand.

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.

Preliminary cost forecasting and optimization for the construction of steel pedestrian bridges in Egypt

PurposeThis research aims to create a methodology that integrates optimization techniques into preliminary cost estimates and predicts the impacts of design alternatives of steel pedestrian bridges (SPBs). The cost estimation process uses two main parameters, but the main goal is to create a cost estimation model.Design/methodology/approachThis study explores a flexible model design that uses computing capabilities for decision-making. Using cost optimization techniques, the model can select an optimal pedestrian bridge system based on multiple criteria that may change independently. This research focuses on four types of SPB systems prevalent in Egypt and worldwide. The study also suggests developing a computerized cost and weight optimization model that enables decision-makers to select the optimal system for SPBs in keeping up with the criteria established for that system.FindingsIn this paper, the authors developed an optimization model for cost estimates of SPBs. The model considers two main parameters: weight and cost. The main contribution of this study based on a parametric study is to propose an approach that enables structural engineers and designers to select the optimum system for SPBs.Practical implicationsThe implications of this research from a practical perspective are that the study outlines a feasible approach to develop a computerized model that utilizes the capabilities of computing for quick cost optimization that enables decision-makers to select the optimal system for four common SPBs based on multiple criteria that may change independently and in concert with cost optimization during the preliminary design stage.Social implicationsThe model can choose an optimal system for SPBs based on multiple criteria that may change independently and in concert with cost optimization. The resulting optimization model can forecast the optimum cost of the SPBs for different structural spans and road spans based on local unit costs of materials cost of steel structures, fabrication, erection and painting works.Originality/valueThe authors developed a computerized model that uses spreadsheet software's capabilities for cost optimization, enabling decision-makers to select the optimal system for SPBs meeting the criteria established for such a system. Based on structural characteristics and material unit costs, this study shows that using the optimization model for estimating the total direct cost of SPB systems, the project cost can be accurately predicted based on the conceptual design status, and positive prediction outcomes are achieved.