Artificial Intelligence and Machine Learning in Construction Springer Nature Link

The findings support the hypothesis that project controllability, which involves bottleneck identification, progress monitoring, and critical path identification, plays a significant role in predicting project delays through the use of machine learning algorithms. Table 7 shows the Fornell-Larcker criterion findings for construct discriminant validity in the evaluation of machine learning algorithms’ ability to forecast project delays in BIM-enabled building projects. With these challenges considered, strong data preprocessing approaches are required on top of developing specialized ML algorithms that can properly interpret and process BIM data . Given the possible results of this research, standard operational procedures can be redefined by including data-driven predictions at the levels of planning and execution of construction projects. Traditional approaches to managing and predicting the timeline of projects have normally been doomed to fail in a dynamic nature of project conditions and complex information data environments . Much strength of BIM lies in the way it allows collaborative project management, integrated datasets in every way possible along the integral life cycle of the construction project .

The evaluation of construction cost prediction models requires a multi-indicator, multi-level approach tailored to the characteristics of the prediction task and the data. Beyond stronger fitting ability, these methods overcome the limitations of traditional approaches that rely on linear relationships https://dineshtripathi.com/the-future-of-home-design-innovative-shapes-and-styles.html or single mechanisms. SVM shows strong generalization ability under small-sample conditions, but its training efficiency becomes limited when applied to large-scale datasets. However, their application is still limited by the need for large datasets and relatively high data requirements in construction cost prediction tasks.

For static cross-sectional data, K-fold cross-validation (K-fold CV) randomly partitions datasets into training and validation subsets and iteratively evaluates model performance, mitigating overfitting from a single data split. Early-stage design decisions act as front-end control variables, establishing basic cost boundaries and producing a “decision upfront, realization later” dynamic. Feature engineering is central to enhancing model performance, including correlation analysis, PCA, and other dimensionality reduction techniques to select key variables, mitigate multicollinearity, and reduce noise. These journals focus on algorithm and intelligent system applications and were most active in the early stages, reflecting the integration of expert systems, neural networks, and other AI techniques into civil engineering research. The study also focused on a limited set of variables and machine learning techniques, which may not have covered all project delay reasons and methods.

Assessing the impact of claims on construction project performance using machine learning techniques

• Methodologically, it leverages a mixed-method approach to establish a validated SEM model that links machine learning constructs to project delay prediction outcomes.
• The quest to build technologies that can imitate human intelligence has been a long-standing aspiration for many industries.
• Existing studies indicate that most construction cost prediction research primarily relies on historical project data as training samples.
• Qualitative analysis indicates that influencing factors in construction cost prediction are complex, interrelated, and dynamic.
• Construction sites are inherently hazardous environments, and traditional safety management relies on human observation and reporting to identify and address risks.
• ML can significantly enhance design processes by tailoring them to user needs.

This study systematically reviewed the research progress of ML and AI in construction cost prediction from 1994 to 2025 by combining scientometric analysis with qualitative synthesis. Furthermore, Transformer- and Long Short-Term Memory (LSTM)-based temporal models are capable of capturing dynamic factors, including fluctuations in material prices and market conditions. In addition, federated learning frameworks can facilitate cross-institutional data collaboration while preserving data privacy, enabling the integration of multi-source datasets (Mohseni et al., 2025). Modeling of external uncertainties, including policy or market volatility, is insufficient (Turkyilmaz and Polat, 2025; Cao and Ashuri, 2020). Construction datasets also typically contain approximately 7% missing values and 5% outliers, directly impacting model training efficiency and stability (Gardner et al., 2016; Lee and Yun, 2024; Sadick et al., 2025; Simić et al., 2023).

Chapter 6 concludes the study, summarizing key findings and providing corresponding research insights. Using VOSviewer, keyword co-occurrence, research hotspots, and academic collaboration networks were visualized to reveal the knowledge structure and evolution of the field (Al Husaeni, 2023). Accordingly, this study aims to provide a comprehensive review of AI and ML applications in construction cost prediction. The data supporting the findings of this study are available on reasonable request from the corresponding author.

The capability of enhancement in BIM through ML is huge, though the implementation of these kinds of advanced technologies may not be devoid of challenges. ML and BIM integration has recently gained considerable attention from the construction industry to solve some of these persistent pains, such as delay, cost overrun, and inefficiency issues. This research proposes a new quantitative framework that incorporates ML algorithms with BIM technology in predicting construction delays. This study is likely to give useful information on practical usage of leading technologies in construction and thus enable better decision-making, enhancing the overall efficiency of projects. Addressing how ML and BIM are integrated may achieve major leaps in construction management by making more real and timely predictions of project delays.

Safety Monitoring and Quality Control Through Machine Learning

Currently, the application of deep learning in construction is limited compared to more established technologies like ML and Building Information Modeling (BIM). https://labrys.ru/en/apartment/panel-house-plan-projects-of-multistorey-houses/ In the construction industry, AI plays a crucial role in turning aspirations into realities by enhancing efficiency, safety, and productivity. Any alternative text (alt text) provided alongside figures in this article has been generated by Frontiers with the support of artificial intelligence and reasonable efforts have been made to ensure accuracy, including review by the authors wherever possible. Strengthening industry collaboration and standardization, including shared datasets, unified evaluation metrics, and deployable engineering tools, will facilitate the transition from laboratory research to practical implementation. Many studies rely on single-project or small-sample datasets—for example, some analyses use only 320 regional samples—resulting in markedly higher MAPE values when models are generalized across regions. In early-stage project decision-making, rapid estimation tools based on ANN, SVM, and related models are widely used in conceptual design and bidding stages.

Machine Learning Application in Construction Delay and Cost Overrun Risks Assessment

Early major journals, including Automation in Construction and Journal of Construction Engineering and Management, appear in blue-green nodes. Using VOSviewer, a minimum threshold of two citations per journal was applied, resulting in 21 core journals selected from 55 sources. Journal co-citation analysis was conducted to reveal the underlying structure of knowledge in ML and AI applications for construction cost forecasting, helping to identify core sources and track the evolution of research themes (Xu et al., 2022).

4 Collaborative frameworks for stakeholder engagement

• Safety is paramount in construction, and ML can elevate safety standards on job sites.
• Currently, the application of deep learning in construction is limited compared to more established technologies like ML and Building Information Modeling (BIM).
• Traditional approaches to managing and predicting the timeline of projects have normally been doomed to fail in a dynamic nature of project conditions and complex information data environments .
• This research proposes a new quantitative framework that incorporates ML algorithms with BIM technology in predicting construction delays.
• Mean scores were calculated to assess the level of agreement, with values above 4.0 considered as strong consensus on construct relevance.

The three main categories of machine learning are supervised learning, where algorithms are trained on labeled data to make predictions; unsupervised learning, where algorithms identify patterns in unlabeled data; and reinforcement learning, where algorithms learn through trial and error to achieve specific goals. Machine learning algorithms analyze large datasets to identify patterns, make predictions, and improve their performance over time without human intervention. In recent years, 3D printing has brought about significant transformations in various sectors, with the construction industry being no exception. From the initial stages to post-project documentation, weather influences everything from… Weather plays a crucial role in the planning, design, and execution of construction projects. As these technologies continue to evolve, their applications will expand, leading to more innovative construction practices.

3 Challenges in handling data and algorithm integration

While previous research has explored ML or BIM in isolation, or only conceptually examined their synergy, this study quantifies the impact of these integrated domains on delay prediction. Delays in projects are considered the most critical concern within the construction industry, as this leads to significant cost overruns and dissatisfaction in project stakeholders . The construction industry has increasingly turned to technological innovations in the quest to tackle inefficiencies and improve project outcomes .

Furthermore, data are often concentrated within a single https://cognifyo.com/articles/electric-rock-drills-performance-safety-sustainability/ country or region, lacking cross-regional validation. Despite significant advances in applying ML and AI to construction cost prediction, practical implementation still faces multi-dimensional limitations. Examples include GRU/LSTM-based highway cost index forecasting models and high-rise building cost estimation systems integrated with BIM attributes. By integrating core parameters such as building area and structural type, these tools can deliver minute-level cost estimates with prediction errors typically controlled within 10%–15%, significantly improving decision efficiency.

VOSviewer was employed to construct an author co-authorship network to reveal collaboration patterns among core researchers in ML and AI applications for construction cost forecasting. The attention of the construction management field toward intelligent cost estimation steadily increased after 2009. As shown in Figure 2, only a few publications appeared between 1994 and 2008, indicating that ML and AI applications in construction cost forecasting were still in the exploratory and theoretical research phase during this period. By analyzing the annual publication counts of the 138 core articles included in this review, the development trajectory and growth trends of ML and AI applications in construction cost forecasting can be clearly illustrated.