1. (Professor, Department of Architecture, KyungHee University)
  2. (Graduate Student, Department of Architecture, KyungHee University)



BIM, Decision Support System, Evaluation Metric

1. Introduction

In the rapidly evolving AEC (Architecture, Engineering, and Construction) industry, innovative technologies are continually reshaping how projects are designed, managed, and executed. One such technology, Building Information Modelling (BIM), has emerged as a game changing tool by enabling comprehensive digital representation of the physical and functional characteristics of construction projects. At the same time, Decision Support Systems (DSS) are increasingly utilized to assist architects and engineers during the design stage by processing vast amounts of data and providing actionable insights. The convergence of DSS and BIM、a fusion of cutting edge technology with construction practices、presents a transformative force that could redefine project design, management, and cost effectiveness in an industry where sustainability, safety, and accuracy are paramount (Ayman et al., 2022). This combination also offers remarkable opportunities to enhance the evaluation and selection of BIM models.

A DSS is a technological tool designed to assist individuals and organizations in making informed and effective decisions (Whyte, 1986). It analyzes large amounts of data to offer actionable insights that can enhance decision making processes. By integrating various data sources, a DSS helps users evaluate complex scenarios and make more accurate, data driven choices. An evaluation metric, a core component of any DSS, is a procedure used to rank items in an extensive database based on user specifications. It plays a central role in a DSS due to its ability to sort items according to user preferences. Several evaluation metrics exist to rank lists of items based on specific user needs. Concisely, scoring functions are measures that condense multidimensional records into a single value, simplifying complex data for recommendation ranking (Skiena, 2017).

The combination of DSS and BIM presents a remarkable opportunity to enhance DSS, optimize workflows, and ultimately transform the construction sector (Asudeh et al., 2019). To ensure that the recommendations provided by these systems are accurate and aligned with user preferences and project objectives, it is essential to have robust assessment metrics in place. This is particularly important when there are multiple options, each with varying degrees of significance, to choose from.

Among the well known metrics, the shortcomings of the frequently use Euclidean scoring is that it suffers from the curse of dimensionality where it becomes outlier-sensitive and assumes orthogonality (Yang & Alessandrini, 2019). The second frequently used distance metric is Cosine similarity which suffers from insensitivity to vector magnitude (Xia et al., 2015).

This study tackles a significant research challenge by exploring the integration of BIM and DSS, both of which have demonstrated considerable potential in their respective domains. As these methodologies have rapidly evolved, there is an increasing demand for their convergence to address complex applications requiring joint outputs. However, the key challenge lies in optimizing their combined efficacy (Tan et al., 2021). The objective of this research is to investigate the optimal use of Euclidean and Cosine similarity measures within a BIM-centric DSS, particularly for managing high-dimensional BIM datasets. The study aims to elucidate how these computational metrics can enhance DSS recommendations, particularly in the construction industry.

2. Literature Review

2.1 Integration of DSS and BIM

The integration of DSS and BIM has amassed attention due to its potential to enhance recommendation systems, particularly in context of AEC industry. DSS provides analytical techniques to process complex data, while BIM offers detailed digital representation of construction projects. Combining these two paradigms enables refined decision making regarding design, cost estimation and project management.

For instance, Fazeli et al. (2020) proposed an integrated BIM-DSS framework for cost estimation, enabling real-time budgeting and financial recommendations. This semi-automated, BIM-based cost estimation offered a flexible and adaptive framework for assessing the financial impact of various design scenarios. The BIM-centric approach demonstrated superior performance compared to traditional methods, particularly in terms of efficiency and accuracy.

A critical aspect of a DSS's effectiveness in processing large datasets is its evaluation metric or scoring function (Boukhayma et al., 2020). These metrics, which are quantifiable measures, play a pivotal role in assessing the efficiency, utility, and output quality of a system within a DSS framework (Hossin & Sulaiman, 2015). By delivering objective, numerical insights, evaluation metrics provide a clear understanding of how well the system achieves its intended goals and requirements. Moreover, they form a crucial link between theoretical models and real-world applications (M. Zhang, 2015; Hastie, 2012). These metrics facilitate a deeper quantitative analysis of the DSS's internal mechanisms, including its accuracy, computational efficiency, and user satisfaction (ENSIAS, Mohammed V, Morocco et al., 2020). Such comprehensive evaluations enable continuous improvement of DSS, ensuring it remains an indispensable tool for decision-making in increasingly complex environments.

Another application of this is in sustainability and energy efficiency in building design by (Fenz et al., 2023) and (Shen et al., 2023), where BIM models are linked with DSS to optimize energy performance. The system simulates various design options, such as HVAC systems or material choices, and provides a decision matrix to help engineers choose the most energy efficient solution. Common tools for this include Green Building Studio and EnergyPlus, with decision evaluation indicators such as energy consumption (kWh/m²/year), CO2 emissions, and LEED certification levels guiding the decision process.

BIM models that incorporate time (4D) and cost (5D) allow project managers to evaluate the effects of schedule changes, cost fluctuations, and resource allocation is yet another case of BIM-DSS integration is in construction scheduling and cost estimation (Kubba et al., 2012). DSS tools like Primavera and Synchro help project managers analyze project timelines, labor costs, and material expenses to develop alternative project scenarios. Decision indicators in this context often include total project cost, project completion time, labor hours, and budget variance. Furthermore, BIM-DSS integration proves useful in disaster management and emergency planning by simulating scenarios such as earthquakes or fires, which help design effective response strategies (Alavi et al., 2022). Systems like ALOHA and Simudyne use BIM data to provide realtime feedback on evacuation routes and structural integrity, with indicators such as time to evacuate, structural safety index, and risk mitigation score.

In facility management and asset maintenance, BIM models linked with DSS are used to predict and plan the maintenance needs of building systems like HVAC or electrical networks. Tools like IBM Maximo and Archibus help managers make data driven decisions on equipment repairs, replacements, and upgrades by evaluating equipment lifespan, failure rates, and maintenance costs (Dashti et al., 2021). Key indicators include equipment downtime, maintenance costs, and life cycle cost. Lastly, urban planning and infrastructure development are increasingly benefiting from BIM-DSS linkages. City planners use these systems to evaluate transportation systems, public facilities, and utilities, allowing for more informed long-term planning. Tools such as InfraWorks and ArcGIS help assess transportation flow, population growth, and environmental impacts, with decision indicators including traffic density, infrastructure cost, environmental impact score, and population growth rate.

The integration of BIM with DSS offers a powerful way to optimize decision making in AEC projects. By linking comprehensive digital models with sophisticated analytical tools, stakeholders can evaluate design alternatives, costs, risks, and sustainability metrics, leading to more informed and data informed decisions across various domains of construction industry.

2.2 Evaluation Metrics in DSS for BIM Assessment

In the context of BIM centered DSS, evaluation metrics are not only essential for processing and interpreting BIM data but also play a pivotal role in ensuring the system provides accurate and meaningful recommendations. The selection of appropriate metrics is critical, as it directly influences the ability of recommendation systems (RS) to effectively rank and compare BIM models based on user specifications, design constraints, and project requirements. A well chosen metric enables the system to capture the nuances of the data. Thereby, aiding in the precision of recommendations and aligning them more closely with user needs.

Although a variety of metrics have been investigated for such applications, Euclidean distance and Cosine similarity remain two of the most frequently employed due to their computational efficiency and effectiveness in handling low dimensional datasets. Euclidean distance calculates the direct, straight line distance between two points in multidimensional space, making it intuitive for spatial comparisons. In contrast, Cosine similarity measures the cosine of the angle between two vectors, which makes it particularly suitable for evaluating the orientation of data points, regardless of their magnitude. This makes Cosine similarity useful in applications where the relative positioning of data, rather than their absolute values, is important.

However, when these metrics are applied to high dimensional BIM datasets, they encounter notable limitations. Euclidean distance, for instance, suffers from what is commonly known as the "curse of dimensionality," where its ability to differentiate between data points diminishes as the number of dimensions increases. This phenomenon causes distances between points to converge, reducing the metric's effectiveness in distinguishing between BIM models with complex, high dimensional attributes. Similarly, Cosine similarity, while proficient at identifying directional relationships in low dimensional spaces, may fail to provide significant differentiation between vectors in high dimensional BIM data, where many points may appear to have similar orientations despite their distinct attributes. These challenges underscore the need for advanced or hybrid metrics to address the intricacies of high dimensional BIM models (Yang & Alessandrini, 2019). To address this, advanced techniques such as dimensionality reduction methods Principal Component Analysis, t-SNE) or hybrid metrics combining multiple measures could be explored. These approaches can better capture the intricate relationships within the data

The concept of "garbage in, garbage out" (GIGO) is particularly pertinent when discussing evaluation metrics for data driven systems, including artificial intelligence and machine learning models (Geiger et al., 2020; Canbek et al., 2022). Inadequate or improperly chosen evaluation metrics can degrade the quality and reliability of a system’s output, potentially leading to flawed decision making. Without appropriate metrics to regulate the system's performance, several critical issues may arise, such as misleading performance assessments or failure to detect input biases (Kilkenny et al., 2018). To mitigate these risks, conducting a thorough sensitivity analysis of the evaluation metrics used in DSS is essential. This involves selecting metrics from a diverse set that captures different dimensions of model performance, depending on the specific problem and domain context. Generic metrics may fail to robustly capture the unique output requirements of complex systems like BIM and DSS, underscoring the need for developing domain specific metrics tailored to the particular nuances of these systems.

In a digital landscape where information is generated at an unprecedented volume and velocity, scoring functions play a crucial role in extracting meaningful insights, thereby facilitating informed, fact based decision making (Asudeh et al., 2019; Stojkovic et al., 2017). These metrics are instrumental in enabling more accurate and effective decisions that lead to improved outcomes (Ayman et al., 2022). Additionally, scoring functions promote the paradigm of continuous improvement by systematically evaluating the system's performance, allowing for ongoing enhancements and adaptability in dynamic environments.

The scope of this study focuses on a comprehensive examination of Minkowski like distance functions, specifically Euclidean and soft cosine distance metrics, which are fundamental evaluation measures widely used in fields such as machine learning, data analysis, and RS. These metrics play a critical role in real world applications like clustering and text document analysis, where they facilitate the measurement of similarity or dissimilarity between data points, contributing to more accurate and efficient model performance (Korenius et al., 2007). Therefore, refining these metrics for domain specific applications will further enhance their effectiveness in complex data environments.

In the context of the modern AEC industry, such study holds undeniable significance. The integration of BIM and DSS is driving a paradigm shift within the construction sector (Nursal et al., 2015a). The fusion of these two technologies offers substantial potential for optimizing workflows across the industry. However, to fully realize these benefits, the establishment of a suitable evaluation criterion is essential, ensuring that the system generates accurate recommendations based on user input. Furthermore, this need aligns with broader technological advancements in BIM, AI, and the construction industry, addressing critical concerns such as safety and sustainability (Boukhayma et al., 2020). BIM based DSS has the potential to dramatically enhance project design and management, ultimately reducing costs and minimizing delays in the high stakes construction environment (Geil, 2011). The integration supported by robust evaluation metrics, represents a transformative approach that can significantly elevate the efficiency and sustainability of the construction industry.

2.3 Practical Implications of Metric Selection

Similarity metrics are extensively utilized in recommendation systems, especially for items with multiple features. These metrics can be optimized and tailored to enhance the performance of DSS in various scenarios. By effectively applying Euclidean and Cosine similarity, the system can better manage complex, multidimensional data and deliver more precise and relevant recommendations.

From a practical standpoint, the selection of evaluation metrics within a DSS has significant implications for the outcomes and overall success of a project. Accurate ranking and selection of BIM models based on user preferences can lead to improved design decisions, directly influencing the quality and efficiency of AEC projects, which are inherently complex and resource-intensive. Consequently, investigating the impact of various evaluation metrics on the performance of BIM-centric DSS is crucial to optimizing decision-making processes in these demanding environments.

In a recommendation system used for suggesting BIM models, user satisfaction is heavily influenced by the accuracy of the system’s recommendations. Therefore, it is crucial to understand the specific conditions under which the aforementioned metrics perform well and identify instances where they may fall short. The literature review examines scenarios where these two metrics demonstrate clear advantages, while also highlighting their potential limitations and drawbacks. This enables professionals to make informed decisions about when and how to apply these measures effectively.

A thorough examination of Euclidean and Cosine similarity metrics across various applications, including BIM models, reveals a significant gap in the literature regarding the lack of comprehensive analysis on how these metrics can be used together within BIM based DSS. This omission is crucial, as it overlooks the potential interactions that may arise from combining the two metrics, especially in handling high dimensional data typical of BIM systems. A deeper understanding of the complementary strengths and potential enhancements offered by integrating these metrics could lead to more effective decision support and recommendation systems in BIM applications (Omar, 2014). This makes the exploration of their combined use a highly valuable area for further research.

Focusing on their effectiveness in handling multifeatured user input, this study aims to clarify how Euclidean and Cosine similarity metrics can be optimized for maximum impact in BIM model DSS. Given that user satisfaction relies on recommendation accuracy, it is crucial to identify the conditions where these metrics perform well and where they fall short (Inhan et al., 2024). A deeper understanding of these metrics will provide valuable insights into their strengths and limitations in complex data environments.

A DSS is a sophisticated information system engineered to assist in making data driven, decision making. DSS leverages advanced algorithms, data analytics, and modeling techniques to streamline decision making processes. By integrating and synthesizing data from multiple sources, DSS processes complex datasets to generate insights, offering clear and actionable information. These systems enhance decision making efficacy by providing an intuitive interface that translates raw data into comprehensive, accessible formats tailored to strategic planning and operational needs. By delivering critical, context specific knowledge they play a pivotal role in recommendations. This contributes to improved overall organizational reputation (Yasnoff & Miller, 2014; W. Holsapple, 2008). Additionally, DSS employs evaluation metrics and scoring functions to systematically assess alternatives, allowing for more informed and quantitatively-backed decision outcomes.

2.4 Theoritical Review

Each evaluation metric offers distinct advantages and limitations depending on the specific context (Linnet, 1988). Drawing from the extensive body of literature on cluster analysis, Euclidean similarity is frequently employed as a reliable method. The effectiveness of Euclidean distance, which underpins Euclidean similarity, is consistently highlighted for its robustness and accuracy in pattern recognition and data clustering applications (Dhawan et al., 2015).

(1)
../../Resources/KICEM/KJCEM.2025.26.2.089/eq1.png

Due to arbitrary scaling caused by small errors in input vectors, Euclidean similarity can inaccurately reflect dissimilarity between vectors. This makes Euclidean distance impractical for use in high dimensional spaces or with large datasets without appropriate adjustments. When dealing with multidimensional vectors, it is crucial to normalize each vector component to mitigate the influence of one component over another, as Euclidean similarity is sensitive to differences in scale.

Cosine similarity is another widely used scoring metric, which ranks items by measuring the angle between their vectors (J. Zhang et al., 2022). Unlike Euclidean distance, this metric is scale-invariant and insensitive to the magnitude of the vectors, making it particularly useful for comparing data regardless of size. Due to its focus on direction rather than magnitude, cosine similarity is considered an unbiased and effective method for analyzing multidimensional data.

(2)
../../Resources/KICEM/KJCEM.2025.26.2.089/eq2.png

The combined Cosine-Euclidean similarity distance measure is a hybrid metric that integrates both cosine similarity and Euclidean distance. This measure captures both angular relationships and magnitude differences between vectors. By balancing the direction sensitive nature of cosine similarity with the magnitude aware Euclidean distance, this metric provides a more comprehensive assessment of similarity. It is particularly useful in situations where both vector orientation and distance contribute to meaningful comparisons, enhancing accuracy in multidimensional or complex datasets. The combined Cosine-Euclidean similarity distance measure is given by

(3)
../../Resources/KICEM/KJCEM.2025.26.2.089/eq3.png

The equation combines both distance measures, effectively balancing their respective influences on the overall similarity score. This hybrid metric enables the consideration of both the position (from Euclidean distance) and direction (from cosine similarity) of data points within a unified distance framework. Consequently, the resulting similarity score is more refined and comprehensive than those derived from either individual metric alone (Mohd & Abdullah, 2018). Alternatively, a parallel approach can be applied, where both similarity metrics are calculated independently, and N items are selected from each ranked list after the ranking process.

Despite advancements in BIM and DSS technologies, there remains a significant gap in comprehensive studies comparing different scoring methods used within DSS for BIM model assessment. Existing research tends to focus either on the implementation of BIM or the independent development of DSS, overlooking the critical influence that various scoring methodologies have on the evaluation processes (Mattiussi et al., 2014, Liu et al., 2019). This gap underscores the need for a systematic study to evaluate and compare these scoring methods, assessing their effectiveness and suitability across diverse application scenarios. There is a notable gap in research regarding studies that utilize a combination of the previously discussed scoring metrics. The potential advantages of integrating Euclidean distance and cosine similarity for item ranking in DSS remain largely unexplored. Existing literature indicates that, when used independently, both metrics often provide inadequate recommendations within DSS frameworks. Despite the scaling sensitivity of Euclidean distance and the magnitude insensitivity of cosine similarity, the two are seldom combined. However, studies suggest that a hybrid scoring function could offer improved similarity scores and more accurate recommendations.

3. Methodology

This study explores the application, benefits, and limitations of evaluation metrics within a DSS for BIM models, focusing on scenarios where one metric may outperform the other. It provides an in-depth analysis of recent advancements and modifications in these distance metrics. Alongside highlighting the strengths of Euclidean distance and cosine similarity, the study also addresses their limitations, particularly in handling high-dimensional data, where challenges related to scaling, normalization, and preprocessing significantly impact their effectiveness.

Fig. 1. Methodology for the study

../../Resources/KICEM/KJCEM.2025.26.2.089/fig1.png

The methodology (as shown in <Fig. 1>) begins with a review of DSS and relevant lit to establish evaluation criteria. Next, evaluation metrics are selected, and the system is assessed based on these metrics. The results are analyzed using ANOVA to identify significant differences. Finally, the metrics are ranked, prioritizing key factors for system performance. This approach ensures systematic evaluation and refinement of the metrics used to assess DSS or similar systems.

Evaluation metrics alone can help identify areas of performance, but without statistical analysis, it's difficult to say if the differences in performance are significant. On the other hand, ANOVA helps to statistically validate whether the differences are meaningful. Combining these tools allows for a comprehensive assessment by measuring performance and then by ensuring that any observed differences are statistically significant. This helps to identify which metrics show variations that are statistically meaningful. Finally, in the last stage, the ranking of evaluation metrics is performed. This ranking allows prioritization of the most important metrics, providing insight into which metrics are most influential in the system's performance. The methodology, as outlined in <Fig. 1> ensures a systematic approach to evaluating and refining the metrics used to assess DSS.

To explore the potential advantages of the hybrid methodology, this study aims to demonstrate how combining Euclidean and cosine similarity metrics can lead to more accurate recommendations within a BIM recommendation system. While the actual implementation of the recommendation system is beyond the scope of this study, the research focuses on establishing a scoring framework that can be easily integrated into such systems. By comparing the performance of individual scoring methods, such as Euclidean distance and cosine similarity, against the combined scoring function, the study evaluates the effectiveness of the hybrid approach. This comparative analysis offers valuable insights into the flexibility of the hybrid scoring algorithm, particularly in enhancing context-awareness and improving suggestion accuracy in recommendation systems.

Fig. 2. A list of scoring measures use in the study

../../Resources/KICEM/KJCEM.2025.26.2.089/fig2.png

<Fig. 2> illustrates the evaluation process for the methodology that leverages multiple similarity scoring methods for data analysis. Data from a central database is processed through different similarity metrics, including Euclidean similarity, cosine similarity, and a combined similarity approach that integrates both. Each of these scoring methods generates results that are then fed into an evaluation framework, where a final score is produced. This score represents a comprehensive assessment, taking into account both quantitative similarities between data points.

The selected metrics were chosen due to their distinct advantages. Euclidean distance is highly sensitive to feature magnitudes, making it suitable for cases where absolute differences between features are critical. In contrast, cosine similarity focuses on the directional relationship between vectors, which is particularly effective when feature magnitudes vary, but the overall direction is the key to similarity. By integrating these two metrics, the hybrid model aims to capitalize on their complementary strengths: Euclidean distance distinguishes items based on feature magnitude, while cosine similarity adds context by emphasizing vector orientation.

The hybrid recommendation approach integrates Euclidean distance and cosine similarity to improve both accuracy and contextual sensitivity. Euclidean distance captures variations in feature magnitudes, whereas cosine similarity emphasizes the orientation of vectors, offering a balance between absolute differences and proportional relationships. This yields accurate recommendations. Alternative metrics, such as Jaccard similarity, Manhattan distance, and Pearson correlation, were excluded due to their limitations in handling complex, multidimensional data or their lack of the versatility and contextual depth afforded by the hybrid model.

3.1 User Input Requirements

The input for DSS consists of 9 choices with multiple sub-options. The menu items include number of floors, minimum area, maximum area, balcony, toilets per floor, number of basements, parking type, façade type and roof type. The input range for each input is constrained. Firstly, the number of floors varies from two to ten, the area varies from 90㎡ to 300㎡. Secondly, the balcony option has only two choices, yes or no for the presence or lack of balcony and the toilets per floor ranges from 3 to 5 where as the number of basement ranges from none to 4. Thirdly, there are two available parking types, namely ground and basement and a total of 8 façade types with only two specific roof types, that is flat and sloped.

The data type for input to the DSS is as following, the building's available space can be anywhere from 90 square meters to 300 square meters and he option for a balcony is a straightforward "Yes" or "No," indicating whether one is present or not. Users can choose between 3 and 5 options for the number of restrooms per floor. There can be as few as one basement and as many as four. While there are two distinct roof types "flat" and "sloped", and a total of eight façade types to choose from when customizing the building design, parking options include "ground" and "basement." This combination of choices leads to a total of (21×2×3×5×8×2) 10,080 unique design choices.

The system is designed to recommend BIM models for office and residential building design based on the input parameters described above. The system links user defined preferences with the BIM model, enabling precise and context aware design recommendations. The system guide final recommendation by presenting the most suitable design options that align with user requirements.

Two scoring functions are used by the DSS to make design recommendations. First, it scores and ranks the options in the database using the weighted norm (weighted Euclidean distance), resulting in the top two design options. In order to arrange the database entries and present the chosen design option, the RS secondly uses cosine similarity. These two scoring methods were selected to make up for each other's shortcomings. When the user input vector is far from the target, the weighted Euclidean distance frequently performs well as compared to cosine similarity. Euclidean distance is given by:

(4)
../../Resources/KICEM/KJCEM.2025.26.2.089/eq4.png

Where xu is the user input vector, xi is the input vector of ith model file in the database, wi is the weight of a particular input feature and is the distance between input features. This can be seen in <Fig. 5> where the distance to all points is calculated for a given point.

(5)
../../Resources/KICEM/KJCEM.2025.26.2.089/eq5.png

Fig. 3. Euclidean similarity score in a feature cluster

../../Resources/KICEM/KJCEM.2025.26.2.089/fig3.png

For the weighted Euclidean distance, a score normalization procedure is established to ensure consistency between the scores produced by these two metrics. The scores from various metrics are made compatible with one another by using the following normalization procedure, which can be universally applied to other metrics if necessary.

The scoring criteria uses Eq. (3) to rank the database in order and yields the first three results to the DSS. An alternative method for the recommendation is to utilized both the scoring metrics independently. The pseudocode for such scoring is as

Similarly, the cosine similarity is given by the following equations.

Fig. 4. Scoring Logic

../../Resources/KICEM/KJCEM.2025.26.2.089/fig4.png
(6)
../../Resources/KICEM/KJCEM.2025.26.2.089/eq6.png
(7)
../../Resources/KICEM/KJCEM.2025.26.2.089/eq7.png

Both the similarity scores as used to generate two ranking for the database. The evaluation criteria return a total for three designs. The first two are returned from the Euclidean distance ranking whereas the last one is selected from the cosine similarity ranking. This is done so as to complement the flaws of the evaluation metrics, as the Euclidean scoring is good at differentiating between spaced clusters of data whereas cosine similarity gives better results for points inside the cluster. Overall, the result from Eq. (3) gives better results and is much simpler to implement.

Fig. 5. Cosine similarity score in a feature cluster

../../Resources/KICEM/KJCEM.2025.26.2.089/fig5.png

If a user's input vector is [6 floors, 200㎡, Balcony: Yes, 4 toilets per floor, 2 basements, Parking Type: Basement, Façade Type 5, Roof Type: Flat], the DSS might identify BIM Model A as an exact match with a distance of zero, BIM Model B as a close second with a minimal distance, and BIM Model C as a highly similar alternative based on cosine similarity.

Fig. 6(a). A DSS Utilizing the Scoring Metric

../../Resources/KICEM/KJCEM.2025.26.2.089/fig6-1.png

<Fig. 6(a)> depicts a user interface for an office space recommendation system. The interface allows users to specify various preferences related to office building design. The tool is intended to help users generate or select office designs based on their individual needs. In the central section of the interface, users can input specific requirements, such as the number of floors, the minimum and maximum area in square meters, whether the office should include a balcony, and the number of toilets per floor. Additionally, there is an option to specify the location of the core, referring to where essential building elements like stairs and elevators should be placed.

The final recommendations presented to the user include three BIM model alternatives: two from the Weighted Euclidean Distance ranking and one from the Cosine Similarity ranking. This ensures that the user receives a comprehensive set of options that cater to both precise and nuanced design requirements. For instance, Design Option 1 would perfectly align with the user's specifications, while Design Option 2 offers a slight variation in area without compromising other key parameters. Design Option 3 provides an alternative that maintains high contextual similarity, beneficial in scenarios where clustered design options offer additional benefits not captured by an exact match.

Fig. 6(b). An NLP based DSS Utilizing the Scoring Metric for Recommending BIM

../../Resources/KICEM/KJCEM.2025.26.2.089/fig6-2.png../../Resources/KICEM/KJCEM.2025.26.2.089/fig6-3.png

<Fig. 6(b)> continues the theme of the office space recommendation system and features another DSS interface. This segment appears to be designed for clients to enter specific details or specifications regarding the office they wish to design. There's a prompt instructing users to "Enter specifications of office," indicating that this section is focused on textual input. Nevertheless the evaluation metrics are utilized in this system to achieve the same result as the DSS shown in <Fig. 6(c)>.

Fig. 6(c). Result of the DSS from hybrid scoring metric

../../Resources/KICEM/KJCEM.2025.26.2.089/fig6-4.png

4. Results and Discussion

This study presents an evaluation metric designed specifically for BIM models. using a combination of both Euclidean distance and Cosine similarity metrics to deliver a precise design recommendation. A carefully constructed uniformly sampled dataset is established to improve the accuracy of the DSS.

The third image represents the output of a DSS in the office space recommendation application. It displays the result in the form a modern office building with sleek glass facades, accompanied by a description of the design. A detailed floor plan outlines the interior layout, illustrating the arrangement of spaces. The recommendation is generated using a hybrid scoring function that assesses user inputs against predefined criteria, ensuring alignment with their preferences. Overall, the evaluation metrics effectively combines client design requirements with a structured decision making approach.

When considering client requirements for a DSS for BIM, several key evaluation indicators must be addressed to ensure that the system meets their expectations and project needs. First, system performance is crucial, as clients will expect the DSS to process and analyze large volumes of BIM data efficiently, providing timely and accurate results to support client needs. The usability of the system is another critical factor, as clients require an intuitive and user friendly interface that allows various stakeholders, including those with limited technical expertise, to navigate and utilize the system easily. This also extends to collaborative features that enhance team communication.

There are some constraints and challenges to consider while creating a DSS for BIM. One limitation is that the effectiveness of the RS is heavily dependent on the database quality and comprehensiveness. If the database is not diverse or is not updated on a regular basis, the result of the system may become less accurate over time. Furthermore, while the system takes into account a wide range of input parameters, it may not capture highly specific or niche design requirements, which may necessitate manual adjustments.

ANOVA was employed to determine if the choice of distance metric significantly affects the DSS's ability to recommend BIM models that meet user specifications. By comparing the means of the distances calculated by each metric, we can assess whether one metric performs better than the others in terms of accuracy and consistency. It was conducted to asses whether there were significant differences between the means of difference design options generated by the DSS. This analysis is aimed to validate the effectiveness of a hybrid scoring method in offering consistent and reliable recommendations. The ANOVA analysis is conducted to evaluate whether there were significant differences between the means of three independent distance metrics, that is, Euclidean distance, Cosine similarity, and a combined distance function, in a DSS. This analysis aimed to validate the effectiveness of a hybrid scoring method that offers consistent and reliable recommendations. The null hypothesis (H₀) assumed that the population means of the three distance functions were the same. Specifically, the means of the Euclidean distance, Cosine similarity, and the combined distance function were denoted by μ₀, μ₁, and μ₂, respectively. The ANOVA test was carried out to determine whether these means differed significantly, comparing the p-value to a significance level (α) of 0.05.

The null hypothesis denoted by H0 shows asserts that population mean of the three distance functions is the same. To put it mathematically:

(8)
../../Resources/KICEM/KJCEM.2025.26.2.089/eq8.png

Where, μ0, μ1, μ2 represent the mean of Euclidean distance, Cosine similarity and the combined distance function, respectively. A simple ANOVA test is conducted to test the H0 by comparing the p-value at α=0.05. A value of 23.28 is obtained for F-Statistic and p-value of 7.12x1e-9. Such a large value of F-statistic and small p-value indicate strong evidence against null hypothesis, implying the difference in mean are highly unlikely due to random chance. The results showed an F-statistic of 23.28 and a p-value of 7.12×10⁻⁹. Given the large F-statistic and the very small p-value, there was strong evidence against the null hypothesis, indicating that the differences in the means were statistically significant and highly unlikely to be due to random chance. The data for the three metrics showed that Cosine similarity had a mean of 0.1711 with a standard deviation of 0.1962, Euclidean distance had a mean of 0.5871 with a standard deviation of 0.2257, and the combined distance function had a mean of 0.3790 with a standard deviation of 0.2892.

The scoring process ultimately provided a reference to BIM models. The combination of Euclidean distance and Cosine similarity offered a balanced method for evaluation, merging the strengths of both metrics. While Cosine similarity excels at capturing semantic relationships, Euclidean distance is effective at recognizing proximity in feature space. This combined approach resulted in more refined recommendations that could better accommodate user preferences. Therefore, the hybrid method proved to be a better evaluation metric as validated by the ANOVA analysis.

Table. 1 Distance metric statistics

Variables

Mean

Std. Dev

Normalized Cosine Distance

0.1711

0.1962

Normalized Euclidean Distance

0.5871

0.2257

Normalized Combined Distance

0.3790

0.2892

The result of the scoring process is a reference to BIM models that can be used as a starting point for creating a detailed site-specific BIM model. For evaluation criteria, combining Euclidean distance and cosine similarity offers a fair method that balances accuracy with variety. While cosine similarity is good at capturing semantic similarities, Euclidean distance is excellent at recognizing things that are close together in feature space. Combining these metrics makes the results more comprehensive, accommodating user preferences. All things considered; this combination makes better decisions by utilizing the advantages of both measurements.

Fig. 7. Box plot for distance metrics

../../Resources/KICEM/KJCEM.2025.26.2.089/fig7.png

4.1 Implications of Findings

The metrics for BIM centered DSS has demonstrated promising accuracy and effectiveness in aligning with user preferences and requirements. The system caters to the diverse needs and preferences of user. The effective use of both weighted Euclidean distance and cosine similarity algorithms ensures that the recommendations are not only varied but also closely tailored to the specific user input.

However, it is critical to recognize that the effectiveness of the DSS is heavily dependent on the scoring algorithm, database quality and diversity. To maintain accuracy with the chosen scoring algorithms, the database must be updated and expanded on a regular basis. Furthermore, the DSS may encounter limitations in situations where input features are less distinguishable, necessitating additional research to address these challenges. The findings demonstrate that this dual-scoring method is highly effective in generating design recommendations that closely align with user preferences, particularly in the context of BIM.

5. Conclusion

This work explores a hybrid methodology for a BIM DSS that combines Euclidean and Cosine similarity metrics, with the goal of improving accuracy and context-awareness. The methodology defines scoring criteria for user input, employs both Euclidean distance and cosine similarity scoring, and assesses their utility. ANOVA test is setup to test they hypothesis which reveals significant differences in the means of the distance functions, with the hybrid approach showing promise. The study emphasizes the significance of scoring metric to provide decision assistance and address potential limitations.

The implemented DSS offers an innovative approach to early design choices for BIM models. This aligns with the concept of informed decision making, which has been largely overlooked in the construction industry. Because of its adaptability and integration with various 3D design tools, it is a valuable asset for intelligent design scenarios.

This study represents an important step toward improving modular BIM design by incorporating DSS. It emphasizes the potential of DSS to improve the architecture and construction industries by streamlining the design process, promoting sustainability, and ensuring user-centered design practices.

In conclusion, the dual scoring approach, which combines weighted Euclidean distance and cosine similarity, has proven effective in providing a range of design options that align with user preferences in terms of accuracy and effectiveness. The success of DSS in matching client requirements with appropriate designs demonstrates its potential to transform the BIM design process, making it more efficient, user-centric, and regulatory-compliant. However, continuous monitoring and updating of the database and algorithms are required to maintain and improve its accuracy over time.

Acknowledgements

Agency for Infrastructure Technology Advancement (KAIA) grant funded by the Ministry of Land, Infrastructure and Transport (Grant RS-2021-KA163269).

References

1 
Alavi, H., Bortolini, R., and Forcada, N. (2022). “BIM-based decision support for building condition assessment.” Automation in Construction, 135, 104117. https://doi.org/10.1016/j.autcon.2021.104117DOI
2 
Asudeh, A., Jagadish, H.V., and Stoyanovich, J. (2019). Towards Responsible Data-driven Decision Making in Score-Based SystemsURL
3 
Ayman, H.M., Mahfouz, S.Y., and Alhady, A. (2022). “Integrated EDM and 4D BIM-Based Decision Support System for Construction Projects Control.” Buildings, 12(3). https://doi.org/10.3390/buildings12030315DOI
4 
Boukhayma, K., Idrissi, M.A.J., and Benhiba, L. (2020). “Evaluating Ongoing Decision Support System: A Case Study.” Proceedings of the 13th International Conference on Intelligent Systems: Theories and Applications, 1-6. https://doi.org/10.1145/3419604.3419802DOI
5 
Canbek, G. (2022). “Gaining insights in datasets in the shade of “garbage in, garbage out” rationale: Feature space distribution fitting.“ WIREs, 12(3). https://doi.org/10.1002/widm.1456DOI
6 
Dashti, M.S., RezaZadeh, M., Khanzadi, M., and Taghaddos, H. (2021). “Integrated BIM-based simulation for automated time-space conflict management in construction projects.” Automation in Construction, 132, 103957. https://doi.org/10.1016/j.autcon.2021.103957DOI
7 
Dhawan, S., Singh, K., and Jyoti (2015). “High Rating Recent Preferences Based Recommendation System.” Procedia Computer Science, 70, 259-264. https://doi.org/10.1016/j.procs.2015.10.085DOI
8 
Benhiba, L., Boukhayma, K., and Idrissi M.A.J. (2020). “Defining a Learning Metric for DSS Success Monitoring.” International Journal of Recent Technology and Engineering, 9(1), 430-436. https://doi.org/10.35940/ijrte.F1150.059120DOI
9 
Fazeli, A., Dashti, M.S., Jalaei, F., and Khanzadi, M. (2020). “An integrated BIM-based approach for cost estimation in construction projects.” Engineering, Construction and Architectural Management, 28(9), 2828-2854. https://doi.org/10.1108/ecam-01-2020-0027DOI
10 
Fenz, S., Giannakis, G., Bergmayr, J., and Iousef, S. (2023). “RenoDSS – A BIM-based building renovation decision support system.” Energy and Buildings, 288, 112999. https://doi.org/10.1016/j.enbuild.2023.112999DOI
11 
Geiger, R.S., Yu, K., Yang, Y., Dai, M., Qiu, J., Tang, R., and Huang, J. (2020). “Garbage in, garbage out?” Proceedings of the 2020 Conference on Fairness, Accountability, and Transparency, 325-336. https://doi.org/10.1145/3351095.3372862DOI
12 
Geil, B.K., and Issa, R.R.A. (2011). “Return on Investment Analysis of Using Building Information Modeling in Construction.” Journal of Computing in Civil Engineering, 27(5). https://doi.org/10.1061/(ASCE)CP.1943-5487.0000164DOI
13 
Hastie, H. (2012). “Metrics and Evaluation of Spoken Dialogue Systems.” Data-Driven Methods for Adaptive Spoken Dialogue Systems, 131-150. https://doi.org/10.1007/978-1-4614-4803-7_7DOI
14 
Holsapple, C.W. (2008). “Decisions and Knowledge.” Handbook on Decision Support Systems 1, 21-53. https://doi.org/10.1007/978-3-540-48713-5_2DOI
15 
Hossin, M., and Sulaiman, M.N. (2015). “A Review on Evaluation Metrics for Data Classification Evaluations.” International Journal of Data Mining & Knowledge Management Process, 5(2), 1-11. https://doi.org/10.5121/ijdkp.2015.5201DOI
16 
Jalaei, F., and Jrade, A. (2015). “Integrating building information modeling (BIM) and LEED system at the conceptual design stage of sustainable buildings.” Sustainable Cities and Society, 18, 95-107. https://doi.org/10.1016/j.scs.2015.06.007DOI
17 
Korenius, T., Laurikkala, J., and Juhola, M. (2007). “On principal component analysis, cosine and Euclidean measures in information retrieval.” Information Sciences, 177(22), 4893-4905. https://doi.org/10.1016/j.ins.2007.05.027DOI
18 
Kilkenny, M.F., and Robinson, K.M. (2018). “Data quality: ‘Garbage in – garbage out.’” Health Information Management Journal, 47(3), 103-105. https://doi.org/10.1177/1833358318774357DOI
19 
Kim、I.H., Shin, J.H., Shah, S.H., and Rehman, S.U. (2024). “Client-centered detached modular housing: natural language processing-enabled design recommender system.” Journal of Computational Design and Engineering, 11(3), 137-157. https://doi.org/10.1093/jcde/qwae041DOI
20 
Kubba, S. (2012). “Green Design and the Construction Process.” Handbook of Green Building Design and Construction, 105-144. https://doi.org/10.1016/B978-0-12-385128-4.00003-2DOI
21 
Leslie, G. (1986). “Decision support systems: Learning to apply computers.” Aslib Proceedings, 38(9), 275-283. https://doi.org/10.1108/eb060048DOI
22 
Linnet, K. (1988). “A review on the methodology for assessing diagnostic tests.” Clinical Chemistry, 34(7), 1379-1386. https://doi.org/10.1093/clinchem/34.7.1379DOI
23 
Liu, D., Chen, X., and Peng, D. (2019).“ Some cosine similarity measures and distance measures between q-rung orthopair fuzzy sets.” International Journal of Intelligent Systems, 34(7), 1572-1587. https://doi.org/10.1002/int.22108DOI
24 
Mattiussi, A., Rosano, M., and Simeoni, P. (2014). “A decision support system for sustainable energy supply combining multi-objective and multi-attribute analysis: An Australian case study.” Decision Support Systems, 57, 150-159. https://doi.org/10.1016/j.dss.2013.08.013DOI
25 
Mohd, W.R.W., and Abdullah, L. (2018). “Similarity measures of Pythagorean fuzzy sets based on combination of cosine similarity measure and Euclidean distance measure.” AIP Conference Proceedings, 1974(1), 030017. https://doi.org/10.1063/1.5041661DOI
26 
Nursal, A.T., Omar, M.F., and Nawi, M. (2015). “Conceptual Design of Fuzzy TOPSIS DSS for Building Information Modeling (BIM).” Advances in Environmental Biology, 9(5), 28-31URL
27 
Nursal, A.T., Omar, M.F., and Nawi, M.N.M. (2015). “The Design Of Topsis4bim Decision Support For Building Information Modeling Software Selection.” Jurnal Teknologi, 77(5). https://doi.org/10.11113/jt.v77.6106DOI
28 
Omar, M.F., Nursal, A.T., Nawi, A., Haron, A.T., and Kai, C. (2014). “A preliminary requirement of decision support system for building information modelling software selection.” Malaysian Construction Research Journal, 15(2), 11-28URL
29 
Rehman, S.U., Kim, I.H., and Choi, J.S. (2024). “Data-drive integration framework for four-dimensional building information modelling simulation in modular construction: a case study approach.” Journal of Computational Design and Engineering, 10(6), 2288-2311. https://doi.org/10.1093/jcde/qwad100DOI
30 
Shen, Y., and Pan, Y. (2023). “BIM-supported automatic energy performance analysis for green building design using explainable machine learning and multi-objective optimization.” Applied Energy, 333, 120575. https://doi.org/10.1016/j.apenergy.2022.120575DOI
31 
Skiena, S.S. (2017). “Scores and Rankings.” The Data Science Design Manual, 95-120. https://doi.org/10.1007/978-3-319-55444-0_4DOI
32 
Stojkovic, I., Ghalwash, M., and Obradovic, Z. (2017). “Ranking Based Multitask Learning of Scoring Functions.” Machine Learning and Knowledge Discovery in Databases, 721-736. https://doi.org/10.1007/978-3-319-71246-8_44DOI
33 
Tan, T., Mills, G., Papadonikolaki, E., and Liu, Z. (2021). “Combining multi-criteria decision making (MCDM) methods with building information modelling (BIM): A review.” Automation in Construction, 121, 103451. https://doi.org/10.1016/j.autcon.2020.103451DOI
34 
Whyte, R.G. (1986). “What is a Decision Support System?” Industrial Management & Data Systems, 86(7/8), 28-30. https://doi.org/10.1108/eb057449DOI
35 
Yang, D., and Alessandrini, S. (2019). “An ultra-fast way of searching weather analogs for renewable energy forecasting.” Solar Energy, 185, 255-261. https://doi.org/10.1016/j.solener.2019.03.068DOI
36 
Yasnoff, W.A., and Miller, P.L. (2014). “Decision Support and Expert Systems in Public Health.” Public Health Informatics and Information Systems, 449-467. https://doi.org/10.1007/978-1-4471-4237-9_23DOI
37 
Zhang, J., Wang, F., Ma, F., and Song, G. (2022). “Text Similarity Calculation Method Based on Optimized Cosine Distance.” 2022 International Conference on Electronics and Devices, Computational Science (ICEDCS), IEEE, 37-39. https://doi.org/10.1109/ICEDCS57360.2022.00015DOI
38 
Zhang, M. (2015). “Evaluation of Information Systems.” Wiley Encyclopedia of Management, 1-3. https://doi.org/10.1002/9781118785317.weom070220DOI