Assessing the Belt and Road Initiative’s Impact: A Multi-Regression Model Based on Economic Interaction

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

Please find my comments below:

The research topic proposed by the authors is current and relevant, in the present context.

The introduction is well-structured, however, I would recommend some more explicit answers to the following questions:

a)     what are the research hypotheses?

b)     how do the results fit in the theory?

 

In my opinion there is not a systematic literature review as stated by the authors, but merely a presentation of the situation.

I suggest that the results should be discussed and interpreted in perspective of previous studies and of the working hypotheses.

I suggest that the conclusions should be concreted by associating with previous studies in the literature and include the recommendations for future research.

Please pay attention to the editing of the text. Correct some words: Otheitis (Line 162), Ofprosp (Line 195) and Indiactor (used by 6 times).

Author Response

The research topic proposed by the authors is current and relevant, in the present context.

The introduction is well-structured, however, I would recommend some more explicit answers to the following questions:

1. what are the research hypotheses?

Response The research hypotheses underpinning this study are as follows:

 

1. Hypothesis 1: The economic interaction between China and the participating countries under the Belt and Road Initiative (BRI) has a positive impact on the GDP of these countries.
2. Hypothesis 2: The implementation of BRI policies enhances the container throughput at ports in the participating countries, thereby improving their overall trade efficiency.

These hypotheses are derived from the underlying assumption that the strategic investments, improved infrastructure, and enhanced trade connectivity facilitated by the BRI contribute significantly to the economic growth and trade capacities of the participating countries.

 

1. b)how do the results fit in the theory?

 

Response The results of this study align well with existing economic and trade theories, particularly those related to international trade, foreign direct investment (FDI), and regional economic integration.

 

1. International Trade Theory: The positive impact of BRI policies on GDP and port throughput supports the classical and new trade theories, which suggest that reducing trade barriers and improving infrastructure can enhance trade flows and economic growth. The findings corroborate the theories that increased connectivity and reduced logistical costs foster greater economic integration and mutual benefits among trading partners.
2. FDI Theory: The positive relationship between Chinese investments and the economic growth of participating countries aligns with FDI theories, which argue that foreign investments bring not only capital but also technology transfer, managerial expertise, and improved productivity. The results underscore the importance of strategic investments in driving economic development.

• Regional Economic Integration: The study’s results also fit within the framework of regional economic integration theories, which posit that economic collaboration and policy harmonization among neighboring countries can lead to enhanced economic performance. The BRI, as a regional initiative, exemplifies how coordinated policies and joint infrastructure projects can yield substantial economic benefits.

In conclusion, the empirical evidence presented in this study substantiates the theoretical propositions of international trade, FDI, and regional economic integration. The positive effects observed on GDP and port throughput highlight the practical implications of these theories in the context of the BRI.

 

In my opinion there is not a systematic literature review as stated by the authors, but merely a presentation of the situation.

I suggest that the results should be discussed and interpreted in perspective of previous studies and of the working hypotheses.

I suggest that the conclusions should be concreted by associating with previous studies in the literature and include the recommendations for future research.

Please pay attention to the editing of the text. Correct some words: Otheitis (Line 162), Ofprosp (Line 195) and Indiactor (used by 6 times).

Response Thank you for your suggestion, the literature review 2.1 on BRI has been updated in its entirety, a discussion of previous studies has been added to the article, and incorrect spellings have been corrected.

Reviewer 2 Report

Comments and Suggestions for Authors

The authors conducted a research based on evaluation of the Belt and Road Initiative's impact. They used the model and PCR and AHP. The paper needs some necessary changes below:

- How specifically does the Belt and Road Initiative impact the economic and shipping performance in Southeast Asia, and can you provide detailed examples or case studies?

- What is the rationale behind selecting the six economic interaction indicators used in your study, and how do they comprehensively represent the economic interactions under the BRI?

- Why was Principal Component Regression chosen to handle multicollinearity in your model, and how does it enhance the robustness of your findings?

- How is the Analytic Hierarchy Process integrated into your research methodology, and what unique insights does it provide?

- Considering the complexities of economic and shipping activities, would advanced time-series analysis methods offer more in-depth insights, and if not, why were they excluded?

- Can the findings of your study be generalized beyond Southeast Asia, and what modifications would be needed to apply your models to other regions involved in the BRI?

- What are the potential areas for future research based on your study's findings, and how can the research be extended to further understand the BRI's impact on global shipping and trade?

- How did you determine the threshold for choosing the first three principal components in the PCR model, and why were these deemed sufficient to represent the data?

- Please mention these two studies in detail in the AHP section in order to give the readers more comprehensive information about AHP analysis and to increase the depth of the article.

Polymeric Materials Selection for Flexible Pulsating Heat Pipe Manufacturing Using a Comparative Hybrid MCDM Approach
https://doi.org/10.3390/polym15132933

A Novel Multi-Criteria Decision-Making Model for Building Material Supplier Selection Based on Entropy-AHP Weighted TOPSIS
https://doi.org/10.3390/e22020259

- The paper mentions that the AHP method was used to adjust regression coefficients. How does this adjustment enhance the interpretability or accuracy of your model's predictions?

- The analysis indicates significant economic interactions between Southeast Asia and China. How do you account for external factors or shocks, like the COVID-19 pandemic, in your model?

- The study concludes that deeper participation in the Belt and Road Initiative leads to more positive economic impacts. How do you differentiate the effects of BRI participation from other economic dynamics or policies in the region?

- Considering the AHP weight adjustments, how stable are the model predictions across different economic scenarios or shocks?

Comments on the Quality of English Language

Minor editing of English language required.

Author Response

The authors conducted a research based on evaluation of the Belt and Road Initiative's impact. They used the model and PCR and AHP. The paper needs some necessary changes below:

- How specifically does the Belt and Road Initiative impact the economic and shipping performance in Southeast Asia, and can you provide detailed examples or case studies?

Response The impact of the Belt and Road Initiative on the economy and shipping industry in Southeast Asia is analyzed in detail in the updated Section 4.5, i.e. the case study analysis, taking into account the findings of the study.

- What is the rationale behind selecting the six economic interaction indicators used in your study, and how do they comprehensively represent the economic interactions under the BRI?

Response The explanation of the selection of indicators of economic interactions has been added to Section 3.2, while the indicators of independent variables have been adjusted from 6 to 10

- Why was Principal Component Regression chosen to handle multicollinearity in your model, and how does it enhance the robustness of your findings?

Response As mentioned in the article, economic data indicators typically exhibit multicollinearity. In the updated Section 4.3, extensive analyses of the correlations among the independent variables were conducted, including the creation of correlation coefficient matrix heatmaps, scatter plots of the distributions of dependent and independent variables, and the calculation of variance inflation factors (VIF). All these analyses confirmed the presence of multicollinearity among the independent variables.

Principal Component Regression (PCR) was chosen to address this issue because of its distinct characteristics. Specifically, PCR transforms the original correlated independent variables into a set of uncorrelated principal components. These principal components are linear combinations of the original variables and capture the maximum variance in the data with the least number of components, thereby reducing dimensionality and mitigating multicollinearity.

By employing PCR, the robustness of the findings is enhanced in several ways:

1. Reduction of Multicollinearity: PCR effectively addresses multicollinearity by using principal components that are orthogonal to each other. This ensures that the regression coefficients are not inflated, which can lead to more reliable and stable estimates.
2. Improved Predictive Accuracy: By focusing on the principal components that capture the most significant variance, PCR improves the predictive accuracy of the model. This is particularly important in economic forecasting, where precise and reliable predictions are crucial.

• Enhanced Model Interpretability: Although PCR involves a transformation of the original variables, it allows for an understanding of which combinations of variables (principal components) are most influential in explaining the variance in the dependent variables. This insight can be valuable for policymakers and stakeholders.

Therefore, Principal Component Regression was selected to handle multicollinearity in the model, ensuring that the findings are both robust and reliable.

- How is the Analytic Hierarchy Process integrated into your research methodology, and what unique insights does it provide?

 

Response In the updated Section 3.3, a more detailed explanation of the Analytic Hierarchy Process (AHP) theory has been provided. The integration of AHP into the research methodology involves using AHP to determine the weights of various indicators. This approach allows for a systematic and hierarchical evaluation of the factors influencing economic outcomes.

 

The AHP process involves structuring the decision problem into a hierarchy, comparing the elements pairwise, and deriving weightings based on these comparisons. By applying AHP, the weights obtained are more objective and reflect the relative importance of each indicator accurately.

 

The integration of AHP provides several unique insights and advantages:

 

1. Enhanced Objectivity: By using a structured and consistent comparison method, AHP minimizes subjective bias in determining the importance of various indicators. This ensures that the weights assigned to each factor are based on rigorous analytical processes.
2. Comprehensive Evaluation: AHP allows for the inclusion of both quantitative and qualitative factors in the evaluation process. This comprehensive approach ensures that all relevant aspects are considered, providing a holistic view of the factors impacting the outcomes.

• Prioritization of Factors: The weights derived from AHP highlight the most critical factors influencing the dependent variables. This prioritization helps in focusing on the key drivers of economic outcomes, which can be particularly useful for policymakers and stakeholders.

1. Improved Decision-Making: By providing a clear rationale for the weights assigned to each indicator, AHP enhances the transparency and credibility of the research findings. This can lead to better-informed decision-making and policy formulation.

 

Thus, the incorporation of AHP into the research methodology allows for a more robust and reliable analysis, ensuring that the results are both comprehensive and insightful.

- Considering the complexities of economic and shipping activities, would advanced time-series analysis methods offer more in-depth insights, and if not, why were they excluded?

Response In this study, Principal Component Regression (PCR) is employed to determine the weights of the independent variables and to quantify the impact of these indicators. The aim was to obtain a clear understanding of the relative importance of each factor, which is essential for formulating effective economic and trade policies.

While advanced time-series techniques offer valuable insights, especially in forecasting and trend analysis, they were not the primary focus of this research. The main objective was to assess the influence of various indicators through a comprehensive multivariate analysis. Time-series methods, although powerful for temporal prediction, may not provide the same level of detail in understanding the interrelationships and relative importance of multiple independent variables simultaneously.

However, recognizing the value of advanced forecasting methods, I have incorporated your suggestion and utilized machine learning techniques, specifically Support Vector Machine (SVM), for predicting future data. This integration has enhanced the completeness of the dataset. The enriched dataset, when applied to the Principal Component Analysis, allows for more robust and reliable extraction of the principal components and further improves the quantification of the indicators' impacts.

- Can the findings of your study be generalized beyond Southeast Asia, and what modifications would be needed to apply your models to other regions involved in the BRI?

Response The findings of this study, while focused on Southeast Asia, have the potential to be generalized to other regions involved in the Belt and Road Initiative (BRI). However, several modifications would be necessary to adapt the models to different contexts.

First, the economic and shipping indicators used in the study are specific to the Southeast Asian context and the unique economic relationships between China and the ASEAN countries. In Southeast Asia, more emphasis was placed on shipping-related indicators due to the region's significant maritime trade activities. To apply these models to other regions, the following modifications would be required:

1. Indicator Selection: The selection of indicators should be tailored to the specific economic and trade characteristics of the new region. Factors such as local economic conditions, trade policies, and regional infrastructure must be considered. For regions with less maritime trade and more land-based logistics, it would be essential to include indicators relevant to land transportation, such as rail and road connectivity, border efficiency, and trade facilitation measures.
2. Data Availability and Quality: The availability and quality of data can vary significantly across different regions. Ensuring access to reliable and comprehensive data is crucial for accurate modeling. This may involve collaborating with local institutions or leveraging international databases to gather the necessary data.

• Contextual Adjustments: Economic and shipping activities are influenced by local policies, cultural factors, and geopolitical dynamics. Adjusting the models to account for these contextual differences is essential. This could involve modifying the weightings assigned to indicators based on region-specific expert input or using localized versions of the Analytic Hierarchy Process (AHP).

1. Validation and Calibration: Before generalizing the findings, it is important to validate and calibrate the models using historical data from the new region. This step ensures that the models accurately reflect the economic realities and can provide reliable predictions.

In conclusion, while the core methodology of using Principal Component Regression and machine learning techniques can be applied to other regions, these modifications are necessary to ensure the models are contextually relevant and accurate. By tailoring the models to the specific characteristics of different regions, including adjustments for different types of transportation and trade activities, the insights gained from this study can be extended to a broader set of countries involved in the BRI.

- What are the potential areas for future research based on your study's findings, and how can the research be extended to further understand the BRI's impact on global shipping and trade?

Response The study provides valuable insights into the impact of the Belt and Road Initiative (BRI) on the economic and shipping activities of Southeast Asian countries. Based on the findings, several potential areas for future research can be identified to further understand the BRI's impact on global shipping and trade:

1. Expansion to Other Regions: Future research could extend the current study's methodology to other regions involved in the BRI, such as Central Asia, Eastern Europe, and Africa. By examining the economic and shipping indicators specific to these regions, researchers can assess the broader impact of the BRI on global trade.
2. Sector-Specific Analysis: Another area for future research is to conduct sector-specific analyses. For instance, investigating the BRI's impact on different industries, such as manufacturing, agriculture, and services, could provide a more detailed understanding of how various sectors benefit from improved trade connectivity and infrastructure development.

• Longitudinal Studies: Conducting longitudinal studies to track the long-term effects of the BRI on participating countries can provide insights into the sustainability and evolving impact of the initiative. This could involve analyzing changes in trade patterns, economic growth, and infrastructure development over an extended period.

1. Impact on Small and Medium Enterprises (SMEs): Future research could focus on the impact of the BRI on SMEs in participating countries. Understanding how improved connectivity and trade facilitation measures affect smaller businesses can provide a comprehensive view of the initiative's economic benefits.
2. Environmental and Social Impacts: Another important area for future research is the environmental and social impacts of the BRI. Investigating how infrastructure projects and increased trade activities influence environmental sustainability and social well-being can offer a holistic perspective on the initiative's effects.
3. Technological Innovations in Shipping and Trade: Research could also explore the role of technological innovations, such as digital platforms, blockchain, and artificial intelligence, in enhancing the efficiency and security of shipping and trade under the BRI. Analyzing the integration of these technologies can provide insights into future trends and opportunities.

• Policy Analysis and Recommendations: Future studies could focus on analyzing the policy frameworks and regulatory measures that facilitate or hinder the BRI's success. Providing policy recommendations based on empirical evidence can help governments and international organizations optimize the benefits of the initiative.

By exploring these potential areas for future research, the understanding of the BRI's impact on global shipping and trade can be further enriched. This extended research can contribute to more informed decision-making and the development of strategies to maximize the positive effects of the BRI on global economic integration.

- How did you determine the threshold for choosing the first three principal components in the PCR model, and why were these deemed sufficient to represent the data?

Response Due to adjustments in the indicators, the current version of the principal components is not limited to three. The process of selecting principal components is detailed in the updated section 4.4.1.

First, eigenvalues are calculated, and principal components with a cumulative explained variance exceeding 85% are chosen. An eigenvalue scree plot was also constructed to identify the "elbow point," which further helped determine the appropriate number of principal components. Principal components located before the elbow point on the scree plot are considered for selection.

The selected principal components are then applied to the regression model for analysis. The statistical results, including T-Value and P-Value, are examined. Principal components with a P-Value less than 0.05 are accepted. Additionally, attention was paid to the R-squared value; if the adjusted R-squared was relatively high, principal components with larger P-Values are also considered acceptable.

Based on this methodology, the study ultimately selected the first four principal components for the PCT model and the first two principal components for the GDP model. This approach ensures that the chosen principal components sufficiently represent the data while maintaining statistical significance and model robustness.

- Please mention these two studies in detail in the AHP section in order to give the readers more comprehensive information about AHP analysis and to increase the depth of the article.

Polymeric Materials Selection for Flexible Pulsating Heat Pipe Manufacturing Using a Comparative Hybrid MCDM Approach
https://doi.org/10.3390/polym15132933

A Novel Multi-Criteria Decision-Making Model for Building Material Supplier Selection Based on Entropy-AHP Weighted TOPSIS
https://doi.org/10.3390/e22020259

Response In the updated Sections 3.3 and 4.4, more detailed information has been added to describe the establishment and analysis process of the Analytic Hierarchy Process (AHP). These updates include a comprehensive explanation of the theoretical framework of AHP and its application in the study.

In Section 3.3, the AHP methodology is thoroughly explained, detailing the steps involved in constructing the hierarchy, selecting criteria and sub-criteria, and calculating the weights through pairwise comparisons. The section provides a step-by-step guide on how the criteria were evaluated and the consistency of the comparisons was checked using the consistency ratio (CR).

Section 4.4 focuses on the application of the AHP results in the context of the study. It demonstrates how the derived weights were integrated into the Principal Component Regression (PCR) model to enhance the robustness and accuracy of the findings. The section also includes the calculations and interpretation of the weights, showcasing their impact on the regression outcomes.

- The paper mentions that the AHP method was used to adjust regression coefficients. How does this adjustment enhance the interpretability or accuracy of your model's predictions?

Response The integration of the Analytic Hierarchy Process (AHP) method to adjust regression coefficients significantly enhances both the interpretability and accuracy of the model's predictions. By incorporating AHP, the regression coefficients become more objective and reflective of the relative importance of each variable as determined through expert judgment and pairwise comparisons.

Moreover, without AHP adjustment, the coefficients restored to the original variable dimensions from PCR can be disproportionately large or small, potentially leading to biased interpretations. The AHP method corrects for this by providing a weighted adjustment that aligns the statistical results with the theoretical framework and practical considerations, ensuring that the model's predictions are both accurate and interpretable.

- The analysis indicates significant economic interactions between Southeast Asia and China. How do you account for external factors or shocks, like the COVID-19 pandemic, in your model?

Response In the study, external factors such as the COVID-19 pandemic were not explicitly included in the initial model. However, future data predictions were made using methods like the Grey Model and Support Vector Machine (SVM). These updated predictions encompass data from both before and after the pandemic, enhancing the model's robustness and inclusivity regarding changes in the external environment.

By incorporating post-pandemic data, the model captures the impact of significant external shocks and adjusts the predictions accordingly. This approach ensures that the results are more resilient to fluctuations and better reflect the dynamic economic interactions between Southeast Asia and China under varying conditions.

- The study concludes that deeper participation in the Belt and Road Initiative leads to more positive economic impacts. How do you differentiate the effects of BRI participation from other economic dynamics or policies in the region?

Response The study concludes that deeper participation in the Belt and Road Initiative (BRI) leads to more positive economic impacts. In the updated indicators, two policy-related categorical variables, RCEP and FTA, were included because these are the most significant policies for analyzing the economic interactions between China and ASEAN countries.

RCEP, the Regional Comprehensive Economic Partnership, is part of the BRI framework, as all ASEAN countries have signed this policy with China. Therefore, there is no need to differentiate it from BRI. Although FTAs (Free Trade Agreements) are not exclusive to the BRI, only two ASEAN countries, Singapore and Cambodia, currently have bilateral FTAs with China, with Cambodia signing as recently as 2022.

By including these variables, the analysis ensures a comprehensive understanding of the major policies impacting the economic interactions between China and ASEAN countries. This methodological approach provides a clearer attribution of the observed positive economic impacts to these significant policies, enhancing the robustness and accuracy of the study's conclusions.

- Considering the AHP weight adjustments, how stable are the model predictions across different economic scenarios or shocks?

 

Response The weights calculated for the selected indicators using the AHP method are relatively stable. External shocks are more prominently reflected in the Principal Component Regression (PCR) model. However, by incorporating machine learning techniques for future data prediction, the principal component coefficients derived from these predictions already account for external variations to a certain extent.

The integration of machine learning ensures that the model is resilient to economic scenarios and shocks. This approach enhances the stability and reliability of the predictions, as the model dynamically adjusts to new data, reflecting potential external impacts. Thus, the combination of AHP weight adjustments and advanced predictive methods provides a robust framework for stable and accurate model predictions across varying economic conditions.

Reviewer 3 Report

Comments and Suggestions for Authors

The summary is clear and concise, containing the most important information.

The introduction articulates the purpose of the study, presenting the general methodology and structure of the paper. The purpose is exploratory in nature and does not formulate any research hypotheses, although the considerations presented in the introduction suggest the possibility of formulating several hypotheses. The literature review presents the genesis of the problem and justifies the choice of relevant indicators (variables) of the model.

The research methods and data sources are described sufficiently. From the point of view of a thorough understanding of the methodology, the cited paper [12] is relevant (Rojanaleekul, V., Pungchompoo, S., & Sirivongpaisal, N. (2022). Trade values predictive model of Southeast Asia under the Belt-Road Initiative. The Asian Journal of Shipping and Logistics, 38(3), 162-172). Essentially, the methodology adopted is based on the approach taken in the paper [12].

The paper does not specify in which environment the analyses (calculations and drawings) were performed.

The results are presented in a correct and readable manner. However, to illustrate the presence of possible collinearity of independent variables, correlation graphs between independent variables should be presented. From the point of view of measures, the most commonly used measure of the presence of collinearity is the VIF (Variance Inflation Factor) (see table 6, table 8). Supplementing Table 2 with the p-value for the given values of the correlation coefficient will facilitate the interpretation of these values. Another method to justify the use of PCA, and indirectly address collinearity, involves performing the Bartlett's test and determining the Kaiser-Meyer-Olkin coefficient.

In terms of methodology, it is also noteworthy that the methodology lacks an inclusion of a test for interdependence among dependent variables. It seems that at least GDP and GNI are correlated... In this situation, the regression equations should be interdependent. Providing appropriate analyses for the interdependence of the PCT, GDP, and GNI variables will dispel possible doubts and further substantiate the results obtained.

Elements of the discussion are presented in the “Results and findings” section and the conclusions. At the same time, the lack of separation of this section is noticeable in the work.

The conclusions are consistent with the results and are not surprising; they are in line with expectations.

The bibliography is sufficient and up-to-date.

Additional comments: The authors noted that the scope of the data (2015-2022) covers the pandemic period. However, this period represents a significant qualitative change that can be seen as a limitation in the informativeness of the modeling performed and the results obtained. This should be explicitly stated in the paper.

In terms of time series analysis, the presence of a trend in the series can be noted. This may indicate that the significant independent variable in the models is the time variable.

Author Response

The summary is clear and concise, containing the most important information.

 

The introduction articulates the purpose of the study, presenting the general methodology and structure of the paper. The purpose is exploratory in nature and does not formulate any research hypotheses, although the considerations presented in the introduction suggest the possibility of formulating several hypotheses. The literature review presents the genesis of the problem and justifies the choice of relevant indicators (variables) of the model.

Response

-Regarding the hypothesis section:

1. Hypothesis 1: The economic interaction between China and the participating countries under the Belt and Road Initiative (BRI) has a positive impact on the GDP of these countries.
2. Hypothesis 2: The implementation of BRI policies enhances the container throughput at ports in the participating countries, thereby improving their overall trade efficiency.

These hypotheses are derived from the underlying assumption that the strategic investments.

The research methods and data sources are described sufficiently. From the point of view of a thorough understanding of the methodology, the cited paper [12] is relevant (Rojanaleekul, V., Pungchompoo, S., & Sirivongpaisal, N. (2022). Trade values predictive model of Southeast Asia under the Belt-Road Initiative. The Asian Journal of Shipping and Logistics, 38(3), 162-172). Essentially, the methodology adopted is based on the approach taken in the paper [12].

The paper does not specify in which environment the analyses (calculations and drawings) were performed.

Response

-The calculations and drawings in the manuscript were performed using PyCharm.

The results are presented in a correct and readable manner. However, to illustrate the presence of possible collinearity of independent variables, correlation graphs between independent variables should be presented. From the point of view of measures, the most commonly used measure of the presence of collinearity is the VIF (Variance Inflation Factor) (see table 6, table 8). Supplementing Table 2 with the p-value for the given values of the correlation coefficient will facilitate the interpretation of these values. Another method to justify the use of PCA, and indirectly address collinearity, involves performing the Bartlett's test and determining the Kaiser-Meyer-Olkin coefficient.

Response

- Regarding the testing for multicollinearity, based on your suggestion, I have added an examination of the correlations among the independent variables in Section 4.3. Figure 3 now includes a heatmap of the correlation coefficients among the independent variables, and Table 5 presents the calculated Variance Inflation Factors (VIF) for these variables.

 

In terms of methodology, it is also noteworthy that the methodology lacks an inclusion of a test for interdependence among dependent variables. It seems that at least GDP and GNI are correlated... In this situation, the regression equations should be interdependent. Providing appropriate analyses for the interdependence of the PCT, GDP, and GNI variables will dispel possible doubts and further substantiate the results obtained.

Response

- Thank you for your insightful feedback. Based on your suggestion, the latest version of the manuscript retains only PCT and GDP as the dependent variables and has excluded GNI. This adjustment addresses concerns regarding potential interdependence among the variables and ensures that the regression equations remain robust and independent. By focusing on PCT and GDP, the analysis is streamlined and provides clearer, more substantiated results.

Elements of the discussion are presented in the “Results and findings” section and the conclusions. At the same time, the lack of separation of this section is noticeable in the work.

Response

- Thank you for your suggestion. I have made adjustments to the corresponding sections in the manuscript based on your feedback. The discussion elements have been clearly separated from the “Results and Findings” section and the conclusions to enhance clarity and structure.

The conclusions are consistent with the results and are not surprising; they are in line with expectations.

Response

-For the results analysis, the case studies in updated Section 4.3 have been fully updated, including interpretations of the coefficients of the independent variables, with particular attention to special years such as the years of significant Chinese investment in Malaysia and the changes during the Covid-19 pandemic.

The bibliography is sufficient and up-to-date.

 

Additional comments: The authors noted that the scope of the data (2015-2022) covers the pandemic period. However, this period represents a significant qualitative change that can be seen as a limitation in the informativeness of the modeling performed and the results obtained. This should be explicitly stated in the paper.

Response

-Thank you for your additional comments. In the updated manuscript, the dataset used for Principal Component Analysis and other analyses includes predicted data. The predicted data spans from 2023 to 2030, with independent variable predictions obtained using the GM(1,1) model and dependent variable predictions for 2024-2030 obtained using the Fruit Fly Optimization Algorithm-Support Vector Machine model (since the 2023 dependent variable data can be collected). Therefore, the entire dataset now covers the complete period from 2015 to 2030, encompassing multiple years before and after COVID-19. This approach ensures a more comprehensive analysis and addresses the limitations previously noted.

 

In terms of time series analysis, the presence of a trend in the series can be noted. This may indicate that the significant independent variable in the models is the time variable.

Reviewer 4 Report

Comments and Suggestions for Authors

Based on the iThenticate report provided along with the manuscript, there is a great similarity with a single paper. Therefore, I firstly recommend a revision first to reduce the similarity rate. Then, a more healthy evaluation of the study can be performed.

%21 similarity with a single resource (Trade values predictive model of Southeast Asia under the Belt-Road Initiative https://doi.org/10.1016/j.ajsl.2022.06.001) excluding abstract, quotes, sources that match less than 1% and sources with matches less than 5 words is much more higher than the acceptable rate of similarity.

Author Response

Based on the iThenticate report provided along with the manuscript, there is a great similarity with a single paper. Therefore, I firstly recommend a revision first to reduce the similarity rate. Then, a more healthy evaluation of the study can be performed.

%21 similarity with a single resource (Trade values predictive model of Southeast Asia under the Belt-Road Initiative https://doi.org/10.1016/j.ajsl.2022.06.001) excluding abstract, quotes, sources that match less than 1% and sources with matches less than 5 words is much more higher than the acceptable rate of similarity.

Response

I sincerely apologize for any inconvenience. To ensure more accurate expression in the previous manuscript, I referenced the wording of other authors. I have since thoroughly revised the content. According to the latest iThenticate report, the similarity rate with the articles you highlighted has been reduced to 2%.

The manuscript now includes more detailed explanations regarding the selection of indicators, structure, data processing, and data analysis. Correspondingly, the expression of the manuscript has been updated. Most importantly, the updated manuscript incorporates a data prediction section to better reflect changes before and after COVID-19, enhancing the robustness of the applied models.

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

Thank you for considering my comments and revising the manuscript accordingly.

 

 

Author Response

Thank you very much for your comments! The entire manuscript has been reviewed for clarity and grammar and double-checked through the Grammarly Premium tool.

Reviewer 2 Report

Comments and Suggestions for Authors

The required changes generally was made.

Comments on the Quality of English Language

Minor editing of English language required.

Author Response

Thank you very much for your comment. 

The entire manuscript has been reviewed for clarity and grammar and double-checked through the Grammarly Premium tool.

Reviewer 4 Report

Comments and Suggestions for Authors

The revised form of the submission seems well improved. I am impressed by the current form of the manuscript. I have seen a problem in line 665. It must be corrected before publication.

 

Author Response

Thank you very much for your positive comment. The update can be found in lines 640-646.