A New Perspective on Financial Risk Prediction in a Carbon-Neutral Environment: A Comprehensive Comparative Study Based on the SSA-LSTM Model

Round 1

Reviewer 1 Report (Previous Reviewer 1)

Thank you for considering my suggestions.

I encourage the authors to read the paper throughout to fix typos. 

Author Response

Review Report (Reviewer 1)

Comments and Suggestions for Authors

Thank you for considering my suggestions.

Comments on the Quality of English Language

I encourage the authors to read the paper throughout to fix typos.

Author's Reply to the Review Report (Reviewer 1)

Dear Reviewer,

Thank you for acknowledging the efforts we have put into revising our manuscript based on your valuable suggestions.

We appreciate your encouragement and have taken it to heart. We have meticulously reviewed the entire paper to identify and correct any typographical errors present.

We are grateful for your precious time and the constructive feedback you have provided. We look forward to any further guidance and feedback you may have.

Thank you once again for your time and effort.

Reviewer 2 Report (Previous Reviewer 2)

Vastly improved version of the article. Suggest to incorporate further comment before publication. 

- abstract. need to state clearly that this is a case study of the wind energy sector in China

- abstract. row 19. suggest to replace "breakthrough" with "superior". based on the data in your paper, it does not look like SSA-LSTM is vastly superior to the other methodologies but rather marginally superior (as shown on figure 3)

- figure 2 and 3 are still not connected with the real world. what do the predicted and true values represent? is it corporate past due loans over 90  days or some other financial metric? need to be specific

- row 32, there is a large literature on the relationship between sustainability / ESG and the economy or finance. One relevant reference applicable for emerging markets is "de Mariz, Finance with a Purpose, Fintech, development and financial inclusion in the Global Economy, 2022, World Scientific Publishing", its introduction and bibliography

Author Response

Review Report (Reviewer 2)

Comments and Suggestions for Authors

Vastly improved version of the article. Suggest to incorporate further comment before publication.

Author's Reply to the Review Report (Reviewer 2)

Dear Reviewer

Thank you for recognizing the improvements made in the revised version of our article. We are committed to enhancing the quality of our manuscript and will certainly take into consideration further comments and suggestions before finalizing it for publication.

We appreciate your time and valuable feedback.

Comments and Suggestions

abstract. need to state clearly that this is a case study of the wind energy sector in China

Author's Reply

Thank you for your valuable feedback. We agree that specifying the focus of our case study in the abstract will provide readers with a clearer context right from the outset.

To address this, we have revised the abstract to explicitly mention that our research is centered on a case study of the wind energy sector in China. This amendment will undoubtedly help in setting a clear framework and focus for our study right from the beginning, allowing readers to appreciate the specific scope and applicability of our research findings.

"...offers a potentially superior approach in financial risk prediction. Our study, focusing on a case study of the wind energy sector in China, situates itself within the growing body of research focusing on the integration of environmental sustainability and financial risk management..."

Comments and Suggestions

abstract. row 19. suggest to replace "breakthrough" with "superior". based on the data in your paper, it does not look like SSA-LSTM is vastly superior to the other methodologies but rather marginally superior (as shown on figure 3)

Author's Reply

Thank you for your insightful feedback on our abstract. We agree that the term "breakthrough" might convey a sense of a substantial leap, which may not be entirely substantiated by the data presented in our study.

In light of your suggestion, we have revised the phrase to more accurately reflect the comparative advantage of the SSA-LSTM model. The abstract now reads, "...offers a potentially superior approach in financial risk prediction," which we believe aligns better with the results depicted in figure 3, indicating a marginal superiority over traditional methods.

We appreciate your attention to detail and your constructive suggestion, which has helped in enhancing the precision and accuracy of our manuscript.

Comments and Suggestions

figure 2 and 3 are still not connected with the real world. what do the predicted and true values represent? is it corporate past due loans over 90 days or some other financial metric? need to be specific

Author's Reply

Thank you for your insightful feedback. We acknowledge that the connection between Figures 2 and 3 and real-world implications needed to be more explicitly defined. To address this, we have incorporated a new paragraph in the "Results Analysis" section, where we elucidate the nature of the predicted and true values represented in the figures. Specifically, we have clarified that these values pertain to the financial risk indicators, such as the percentage of corporate loans past due over 90 days, which is a critical metric in assessing financial stability and credit risk. We believe this addition will provide a clearer context and enhance the comprehensibility of the results presented.

We appreciate your time and effort in helping us improve the quality of our manuscript.

Comments and Suggestions

row 32, there is a large literature on the relationship between sustainability / ESG and the economy or finance. One relevant reference applicable for emerging markets is "de Mariz, Finance with a Purpose, Fintech, development and financial inclusion in the Global Economy, 2022, World Scientific Publishing", its introduction and bibliography

Author's Reply

Thank you for pointing out the significant reference that can be included to enrich the discussion on the relationship between sustainability/ESG and the economy or finance, particularly in the context of emerging markets. We appreciate your recommendation of the work by de Mariz (2022), and we plan to integrate insights from this source into our discussion to provide a more comprehensive view of the current trends and developments in the field. This addition will certainly enhance the depth of our literature review and provide a more rounded perspective on the topic at hand.

Here are the specific changes made to incorporate the reference to de Mariz's book:

Introduction of the Financial Sector's Paradigm Shift

Original: (Not Mentioned)

Revised: "In this context, the financial sector is undergoing a paradigm shift, influenced by the rise of FinTech, which is reshaping financial services and fostering greater financial inclusion, especially in emerging markets."

Detailing the Characteristics and Impacts of the Paradigm Shift

Original: (Not Mentioned)

Revised: "This shift, characterized by increased competition from non-traditional actors and a revolution in customer experience, presents both opportunities and challenges, including the potential to alleviate inequality and foster economic development [de Mariz, 2022]."

Integration of FinTech into the Climate Response Strategy

Original: "In reaction, multiple nations have adopted carbon-neutral strategies, aiming for net-zero carbon emissions by 2050. This significant transition influences production and consumption patterns, presenting both opportunities and challenges to the financial system [4]."

Revised: "In reaction to the climate crisis, multiple nations have adopted carbon-neutral strategies, aiming for net-zero carbon emissions by 2050. This significant transition influences production and consumption patterns, presenting both opportunities and challenges to the financial system [4]. Particularly, the financial sector, leveraging the advancements in FinTech, can play a pivotal role in steering investments towards sustainable initiatives, such as the wind energy sector in China."

Reviewer 3 Report (Previous Reviewer 3)

In my opinion 3 changes should take place in order to make this paper more publishable.  First, in lines 200 through 400 the various risks should have supporting references.  Second, you should look in to the efficiency of wind power in China and include something about whether or not it is energy positive [producing more energy than it uses].  Third, while it is helpful that you have provided some general suggestions for future research, it would be useful for you to provide additional specific suggestions for future research.

Author Response

Review Report (Reviewer 3)

Comments and Suggestions for Authors

In my opinion 3 changes should take place in order to make this paper more publishable.  First, in lines 200 through 400 the various risks should have supporting references.  Second, you should look in to the efficiency of wind power in China and include something about whether or not it is energy positive [producing more energy than it uses].  Third, while it is helpful that you have provided some general suggestions for future research, it would be useful for you to provide additional specific suggestions for future research.

Author's Reply to the Review Report (Reviewer 3)

Dear Reviewer,

Thank you for your insightful suggestions that aim to enhance the quality and depth of our manuscript. We appreciate your time and effort in reviewing our work. Here is how we plan to address each of the points you raised:

Supporting References for Various Risks (Lines 200-400): We acknowledge the necessity of substantiating the discussed risks with credible references to provide a robust foundation to our arguments. We will revisit the mentioned lines and enrich the section with pertinent references that corroborate the risks discussed. This will not only strengthen the validity of our claims but also provide readers with avenues to explore the topic further.

Efficiency of Wind Power in China: We agree with your suggestion to delve deeper into the efficiency of wind power in China, particularly focusing on its energy positivity - whether it produces more energy than it consumes. This aspect indeed holds significant relevance to our study as it directly impacts the financial dynamics associated with the wind energy sector. We will conduct a thorough investigation into recent studies and statistical data to present a well-rounded view of the current state of wind power efficiency in China and incorporate this analysis into the relevant sections of our paper.

Specific Suggestions for Future Research: We understand the importance of guiding future research with specific suggestions that stem from our study's findings. To this end, we will expand the concluding section of our paper to include more detailed and specific suggestions for future research. These suggestions will aim to explore uncharted territories and unanswered questions in the domain of financial risk management in the context of climate change, thereby fostering a richer and more nuanced discourse in future studies.

We are confident that these revisions will enhance the depth and breadth of our study, making a more substantial contribution to the existing body of knowledge. We sincerely hope that these improvements will meet your expectations and elevate the quality of our manuscript to a level suitable for publication.

Thank you once again for your valuable feedback.

Round 2

Reviewer 2 Report (Previous Reviewer 2)

* Well done incorporating most of the comments. 

* That said, Fig 2 and Fig 3 are still not clear to the reader. Figures are very important as they illustrate your reasoning and can be easily cited. On the x axis, what is time? is this a period? if so, what period / months? On the y axis, what is the value, if this is corporate PDL above 90 days, then please indicate this. however, how can PDL 90 days be negative? what does the 0 to 120 scale represent? This is important to explain to the reader what financial risk variable you are actually testing. this is not clear from the figures. 

Author Response

Dear Reviewer,

Thank you for your insightful feedback and constructive comments on our manuscript. We appreciate the time and effort you have invested in reviewing our work. Your suggestions have indeed shed light on critical areas where our manuscript can be further refined to convey our research more clearly and accurately. We understand the importance of providing a comprehensive and detailed explanation of the figures presented in our study, especially in illustrating the deep learning computations and the financial risk variables being analyzed. To this end, we have undertaken significant revisions to address your concerns and enhance the clarity and depth of our manuscript. Here, we would like to address your comments point-by-point to elucidate the modifications and clarifications we have incorporated in response to your valuable feedback:

Explanation regarding the X-axis "time":

Reviewer's Query:

On the x-axis, what is time? Is this a period? If so, what period/months?

Author's Reply:

You've raised a pertinent point. On the X-axis, the term "time" denotes individual time points within our dataset, representing a continuous time series. In our deep learning model, this time series data is arranged in chronological order, where each time point signifies a specific time interval, such as a month or a quarter. We will specify this time interval clearly to facilitate a better understanding of how our model evolves over time.

Explanation regarding the Y-axis "value":

Reviewer's Query:

On the y-axis, what is the value? If this is corporate PDL over 90 days, then please indicate this. However, how can PDL over 90 days be negative? What does the scale from 0 to 120 represent?

Author's Reply:

You are correct in noting that the Y-axis represents the percentage of "corporate loans past due over 90 days", a significant metric we are utilizing to assess financial risk. Regarding the occurrence of negative values, this could potentially be a result of normalization or other data transformation techniques applied during the data preprocessing phase. In the training process of deep learning models, we sometimes employ these techniques to enhance the performance and stability of the model. We will revisit our data processing steps and provide more information and clarification about the potential occurrence of negative values in the figure caption. Meanwhile, the scale of 0 to 120 is determined based on the minimum and maximum values present in our dataset, offering a comprehensive view to evaluate the predictive performance of our model.

Clarification on the financial risk variable being tested:

Reviewer's Query:

This is not clear to the reader what financial risk variable you are actually testing.

Author's Reply:

The financial risk variable we are testing is the percentage of corporate loans past due over 90 days, a commonly used financial risk indicator that helps us evaluate the financial health and potential financial risks of a corporate entity. Our deep learning model aims to predict future values of this variable, assisting financial analysts and decision-makers in better understanding and managing financial risks.

We will ensure to clearly indicate this information within the charts and figure captions to provide readers with a better understanding of our research and findings. Thank you once again for your valuable insights and suggestions.

Modification to the Section Describing Figure 2 and 3:

Regarding the X-Axis (Time):

"In our analysis, the X-axis labeled as 'time' represents discrete time intervals during which the data was collected and analyzed. Each point on this axis corresponds to a specific period, which, for the purpose of this study, we have denoted in months. This chronological representation allows us to meticulously track and analyze the trends and patterns in the financial risk variables over a sustained period. This time-series data is crucial in training our deep learning model, enabling it to identify potential patterns and make more accurate predictions for future intervals. We will ensure to annotate the specific time periods on the X-axis in the revised version of the figures to provide a clearer understanding of the temporal scope of our analysis."

Regarding the Y-Axis (Value):

"The Y-axis in Figures 2 and 3 denotes the values of the 'corporate loans past due over 90 days' metric, a significant indicator in financial risk analysis. This metric is represented as a percentage, with the scale ranging from 0 to 120 to encompass the entire range of values observed in our dataset. We acknowledge that the representation of negative values in the graph needs further clarification. These values can occur due to the normalization techniques applied during the data preprocessing phase, which is a common practice in deep learning computations to enhance model stability and performance. We will revisit our data processing steps to provide a more detailed explanation of this phenomenon in the figure captions, ensuring a comprehensive understanding of the depicted values."

Clarification on the Financial Risk Variable Being Tested:

"The primary financial risk variable under scrutiny in our study is the percentage of 'corporate loans past due over 90 days'. This metric serves as a reliable indicator of potential financial instability within a corporate entity, thereby being a focal point in our predictive analysis. Our deep learning model, specifically the SSA-LSTM model, is designed to forecast the future values of this variable, offering a powerful tool for financial analysts and stakeholders to anticipate potential financial downturns with greater accuracy. This, in turn, facilitates more informed decision-making in financial management and policy formulation. We will elucidate this aspect further in the manuscript to provide readers with a clear understanding of the financial risk variable being analyzed and its significance in the context of our study."

Round 3

Reviewer 2 Report (Previous Reviewer 2)

well done. no further comments.

This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.

Round 1

Reviewer 1 Report

Although the study seems a promising attempt, it fails from certain fundamental elements. Here are my comments:

An abstract is the forefront element of a study. Therefore, the authors should clearly address the study's goal in the abstract. The contribution of the study is not clear. In addition, the literature is not presented comprehensively. The authors should reorganize the literature to address the gap that the existing study attempts to fulfill.  Furthermore, policy implications should be discussed from a broader perspective. 

The flow of the article should be strengthened.  

Reviewer 2 Report

The paper is well written and follows good practices in terms of presentation. However the argument suffers from a poor problematic and absence of definition of terms. What is the paper advancing or solving for? What kind of "decision-making" or "financial risk" is studied? The use of big data is interesting but there is a missing link between a technical discussion on statistical models and a real world conclusion. How do the authors infer from a case study on 30 companies in the wind energy sector in China that this statistical approach is superior for credit risk management?

row 19-20-21. Consider what stream of research your paper is inserted in and contributes to.

row 33 "the financial sector has accentuated risks". this is a strong hypothesis. Is there a reference? can you be more specific on how/why it has accentuated those risks? is the financial sector a real sector or just an intermediary (there is ample literature on this topic)? how do you think the banking sector is involved? which functions of the bank participate in this risk (lending, asset management etc)?

row 34. "decision making" how do you define this? this is central to your argument. what kind of risk are you discussing in the paper? what kind of decision maker are you helping with this research? lacking definition

row 113-114. you need to be specific on the scope of research for the sources

row 115. what is "meticulous filtering"? suggest to be specific and mention research methodologies. AI-based retrieval strategy is interesting, but you need to be transparent about filters and potential biases. what does LDA perform? Are there risks or limitations to this method that you are aware of?

row 165 "their role is to align". suggest to review wording, this is not the main role of financial institutions

row 191-192. business have to manage more than just market risk. consider a framework such as BIS' to approach the categories of risks covered 

row 404. the industry that was studied only appears here, this is central to your study and should come in the abstract and intro. 

row 431. the type of financial risk only appears here (credit risk, as per CDB), this is central to your research and should appear earlier

row 419. "million kilo" = giga

row 592. table 4. what are the values in the chart, what is the "estimated" and the "true" value representing? what is on the X and Y axes?

Reviewer 3 Report

Climate change is widely considered as the paramount global challenge of the 21st century, bringing economic, social, and environmental impacts due to rising global temperatures, more frequent extreme weather events, and ecosystem disturbances. To combat this, many countries seek to achieve net-zero carbon emissions by 2050, reshaping both the financial system and consumption patterns. This transition has sharpened the financial sector's focus on climate-related risks, making the carbon footprint, environmental benefits of investments, and sustainability of financial products critical in investors' decisions. However, conventional risk prediction methods may not fully capture these climate-associated risks in a carbon-neutral setting. Emerging from this context is the need for innovative predictive tools. Recently, Long Short-Term Memory networks (LSTM) have gained prominence for their efficacy in time-series forecasting. Singular Spectrum Analysis (SSA), effective for extracting time series patterns, combined with LSTM as SSA-LSTM, offers a potential breakthrough in financial risk prediction. Our study emphasizes the utility of SSA-LSTM in the carbon-neutral landscape, revealing its superiority over traditional methods and providing a robust framework for addressing financial risks in the current carbon-neutral global trend.  The paper is well written and specific comments follow:

1. In line 26 to 28 you should provide several references to works arguing that climate change is the paramount challenge of the 21st century.  While there are many who may agree with you about this, there may also be other factors/challenges that may be considered more important by some individuals.

2. From lines 134 to 290 you should consider adding additional peer reviewed articles supporting the statements that you have made as well as build in a section bridging the current paper in to the literature of Sustainability.

3. In line 280 I am not sure why you have used the word "Chapter' as this is a paper and shall become an article.

4. In the case selection starting on line 401 it might be useful for you to provide references as to why you would choose to examine wind power generation.  Having been involved in research on alternative energy going back to 1980 much wind power tends to be energy negative rather than neutral or positive - meaning that it uses more energy than it generates.  If this is not true in China it would be meaningful to know this.

5. From lines 429 to 462 it would be useful for you to provide peer reviewed references supporting each of your points.

6. In the conclusions section it would be useful for you to provide additional specific suggestions for future research.  This is typically where you are able to make a meaningful difference in future research.

Thank you very much for submitting your paper to Sustainability and thus allowing me to provide comments and suggestions about your paper.  I hope that you find them useful at improving your paper and that you continue to consider Sustainability as an outlet for your finest works in the future.