Comprehensive financial health assessment using Advanced machine learning techniques: Evidence based on private companies listed on ChiNext

Wen Zhu; Meiling Li; Chengcheng Wu; Shanqiu Liu

doi:10.1371/journal.pone.0314966

Peer Review History

Original SubmissionJuly 12, 2024
14 Aug 2024 Decision Letter - Levent ÇALLI, Editor PONE-D-24-28763Comprehensive Financial Health Assessment Using Advanced Machine Learning TechniquesPLOS ONE Dear Dr. Li, Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process. Please submit your revised manuscript by Sep 28 2024 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file. Please include the following items when submitting your revised manuscript: A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'. An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'. If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter. If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols. We look forward to receiving your revised manuscript. Kind regards, Levent ÇALLI, Ph.D Academic Editor PLOS ONE Journal Requirements: 1. When submitting your revision, we need you to address these additional requirements. Please ensure that your manuscript meets PLOS ONE's style requirements, including those for file naming. The PLOS ONE style templates can be found at https://journals.plos.org/plosone/s/file?id=wjVg/PLOSOne_formatting_sample_main_body.pdf and https://journals.plos.org/plosone/s/file?id=ba62/PLOSOne_formatting_sample_title_authors_affiliations.pdf 2. Please note that PLOS ONE has specific guidelines on code sharing for submissions in which author-generated code underpins the findings in the manuscript. In these cases, we expect all author-generated code to be made available without restrictions upon publication of the work. Please review our guidelines at https://journals.plos.org/plosone/s/materials-and-software-sharing#loc-sharing-code and ensure that your code is shared in a way that follows best practice and facilitates reproducibility and reuse. 3. Thank you for stating in your Funding Statement: This research was supported by The Key Discipline Research Capacity Enhancement Project of the Guangdong Provincial Department of Education in 2021 (Project Number: NO.2021ZDJS133); The Guangdong Provincial Undergraduate Teaching Quality and Teaching Reform Project for 2022 (Project Number: [2022] No. 263); The 2020 Institutional Key Discipline Funding (Second Batch) (Project Number: [2020] No.114). Please provide an amended statement that declares all the funding or sources of support (whether external or internal to your organization) received during this study, as detailed online in our guide for authors at http://journals.plos.org/plosone/s/submit-now. Please also include the statement “There was no additional external funding received for this study.” in your updated Funding Statement. Please include your amended Funding Statement within your cover letter. We will change the online submission form on your behalf. 4. We note that your Data Availability Statement is currently as follows: All relevant data are within the manuscript and its Supporting Information files. Please confirm at this time whether or not your submission contains all raw data required to replicate the results of your study. Authors must share the “minimal data set” for their submission. PLOS defines the minimal data set to consist of the data required to replicate all study findings reported in the article, as well as related metadata and methods (https://journals.plos.org/plosone/s/data-availability#loc-minimal-data-set-definition). For example, authors should submit the following data: - The values behind the means, standard deviations and other measures reported; - The values used to build graphs; - The points extracted from images for analysis. Authors do not need to submit their entire data set if only a portion of the data was used in the reported study. If your submission does not contain these data, please either upload them as Supporting Information files or deposit them to a stable, public repository and provide us with the relevant URLs, DOIs, or accession numbers. For a list of recommended repositories, please see https://journals.plos.org/plosone/s/recommended-repositories. If there are ethical or legal restrictions on sharing a de-identified data set, please explain them in detail (e.g., data contain potentially sensitive information, data are owned by a third-party organization, etc.) and who has imposed them (e.g., an ethics committee). Please also provide contact information for a data access committee, ethics committee, or other institutional body to which data requests may be sent. If data are owned by a third party, please indicate how others may request data access. 5. PLOS requires an ORCID iD for the corresponding author in Editorial Manager on papers submitted after December 6th, 2016. Please ensure that you have an ORCID iD and that it is validated in Editorial Manager. To do this, go to ‘Update my Information’ (in the upper left-hand corner of the main menu), and click on the Fetch/Validate link next to the ORCID field. This will take you to the ORCID site and allow you to create a new iD or authenticate a pre-existing iD in Editorial Manager. Please see the following video for instructions on linking an ORCID iD to your Editorial Manager account: https://www.youtube.com/watch?v=_xcclfuvtxQ [Note: HTML markup is below. Please do not edit.] Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: Yes Reviewer #2: Yes ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes Reviewer #2: Yes ****** 3. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified. Reviewer #1: Yes Reviewer #2: Yes ****** 4. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here. Reviewer #1: Yes Reviewer #2: Yes ****** 5. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: The article "Assessing comprehensive financial health using advanced machine learning techniques" has a fairly close customer approach, the research method used is appropriate, ensuring the achievement of the research objectives. There are many contributions to theory and practice. Reviewer #2: Dear authors, I am glad I have this opportunity to review your manuscript entitled "Comprehensive Financial Health Assessment Using Advanced Machine Learning Techniques". My comments/notes are as follows: Title - be more specific and identify the area and/or time period you are focusing on Abstract - clearly identify the aim of your study/research - more focus on the methodology description and add other important information (be more specific) - findings are too general (model can effectively differentiate....; validity of the proposed framework in practical applications is verified ...) - explain the acronym "ST" Introduction - what is a research question you are answering on? what is a research gap that will be solved by your research? - add more relevant sources (3 is not enough) - clearly identify the aim of your study/research - highlight the structure of your manuscript Theoretical Framework and Research Hypotheses H1, H2 - there are too many variables in one hypothesis and it this was the hypotheses cannot be evaluated correctly (focus on 2 variables for each hypotheses) H1, H2 - how it will be verified? ("...and inconsistent trends in these areas may signal unhealthy profits") H3, H4 - how it will be verified? ("When inconsistent trends are exhibited in these two areas, it may indicate unhealthy profit signals.") - each hypothesis should be explained/described using another research results (why you are expecting the relationship between these indicators?) The current description represents your own point of view that should be support by other authors/researchers. - add information about the number of hypotheses in the abstract and the introduction - the overarching model hypothesis H - what is a purpose/idea of its formulating? Methodology - a separate section focusing on the methodology is missing - some information are mentioned in the section "Theoretical Framework and Research Hypotheses", other ones in the section "Empirical Research) - from my point of view, the separate section should be created with all information required Empirical Research - Sample Selection and Data Collection - identify the number of subjects that are evaluated, describe them - Variable definitions - identify the units for each variable + add information about the time period evaluated - Descriptive statistics - the figures should be prepared with better quality, why not all variables are described? - Correlation Analysis - the CA should be included in the methodology Empirical Results Analysis and Robustness Test - highlight the structure of this section on its beginning - Table 3 - move it as an annex Theoretical Application - the title should be changed (the content is different) Conclusion - add information about the limitations of the research presented Formal - check the journal template I wish all the best with this manuscript and other ones in the future. ****** 6. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy. Reviewer #1: No Reviewer #2: No ******** [NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.] While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step. https://doi.org/10.1371/journal.pone.0314966.r001
Revision 1
9 Oct 2024 Author Response Respected reviewers: We offer our deepest and most sincere gratitude to you and express our heartfelt appreciation for your highly valuable professional insights. Upon receiving your revision suggestions, our research team has undertaken an in-depth and systematic examination and revision of the article with an unwaveringly rigorous and scientific stance. The following are our detailed responses to each of your revision suggestions. Title - be more specific and identify the area and/or time period you are focusing on Reply: Based on your suggestion, we have added “Evidence based on private companies listed on ChiNext ” at the end of the title Abstract - clearly identify the aim of your study/research Reply: Based on your suggestions, we have added relevant descriptions, such as “designed to aid investors in pinpointing enterprises boasting sound financial conditions, thereby averting investment losses stemming from financial fraud or earnings management. ” - more focus on the methodology description and add other important information (be more specific) Reply: Based on your suggestions, we have added a description of the research methods, such as ”which can construct a strong learner through iteration and possess the characteristics of high accuracy and strong resistance to excessive fitting. ” - findings are too general (model can effectively differentiate....; validity of the proposed framework in practical applications is verified ...) Reply: This article mainly tests the applicability of the financial health model proposed in this article through ST and ST companies. In 2022, there are 75 ST or ST private listed companies in the Shanghai and Shenzhen stock markets, 72 of which were identified as financially sub-healthy or financially unhealthy, with an accuracy rate of 96%. It shows that the financial health model proposed in this article is feasible and can identify which companies are financially healthy and which companies are financially unhealthy. - explain the acronym "ST" Reply: Based on your suggestion, we have added footnotes to explain "ST" and "ST"，like that "ST" stands for "Special Treatment", indicating a company with abnormal financial conditions or other issues. "ST" means "Special Treatment with a warning of possible delisting", suggesting the company's financial situation is extremely unstable and there's a significant risk of delisting. Introduction - what is a research question you are answering on? what is a research gap that will be solved by your research? Reply: In this section, we mainly want to explain the importance of research on corporate financial health. Current research on financial health is only limited to the surface of financial indicators. It does not deeply study the relationship and linkage changes between various indicators, and lacks a comprehensive and highly operational method. Assessment methods. This article uses the signal transmission theory and the linkage influence of the corresponding indicators, combined with the Z-value model to comprehensively evaluate the financial health of the company, and constructs a feasible and easy-to-operate evaluation method using a combination of dynamic and static methods. The relevant description has been added to the article. - add more relevant sources (3 is not enough) Reply: Based on your suggestion, we have added more relevant sources in the article. - clearly identify the aim of your study/research Reply: Based on your suggestion, we have added some descriptions “offers an important assessment tool for financial conditions and risks to corporate stakeholders.” - highlight the structure of your manuscript Reply: Based on your suggestion, we have added some descriptions ”The article introduces, analyzes empirically, and applies the financial health model through seven chapters: Introduction, Literature Review, Theoretical Framework and Research Hypotheses, Methodology, Empirical Research, Empirical Results Analysis and Robustness Test, Application and Expansion.” Theoretical Framework and Research Hypotheses H1, H2 - there are too many variables in one hypothesis and it this was the hypotheses cannot be evaluated correctly (focus on 2 variables for each hypotheses) Reply：Taking hypothesis 1 as an example, H1: The relationship between the growth rate of sales revenue and the growth rate of accounts receivable significantly affects the profit health of a company, and inconsistent trends in these areas may signal unhealthy profits. In this hypothesis, the growth rate of sales revenue and the growth rate of accounts receivable are independent variables, and the profit health is the dependent variable. This hypothesis is to illustrate that inconsistent changes in the two variables will affect the profit health. This article analyzes whether the direction of change between the two variables is consistent and quantifies it as a criterion for judging whether profits are healthy. Rather than studying the impact of a single variable on another variable. H2 has the same logic. H1, H2 - how it will be verified? ("...and inconsistent trends in these areas may signal unhealthy profits") Reply: In the logic of financial accounting, based on the one-to-one correspondence between each accounting account in the double-entry accounting method and the logical relationship between statement items, an enterprise that is continuously profitable and developing well will have accounts receivable and operating Revenue (H1), operating income and net cash flow from operating activities (H2), net profit and inventory turnover rate (H3), total profit and gross income (H4), the direction of change between the four pairs of financial indicators should be consistent , this is common sense logic. If there are inconsistencies, there may be some manipulation or negative operating conditions, which are signs of unhealthy profits. H3, H4 - how it will be verified? ("When inconsistent trends are exhibited in these two areas, it may indicate unhealthy profit signals.") Reply: Same reply as above - each hypothesis should be explained/described using another research results (why you are expecting the relationship between these indicators?) The current description represents your own point of view that should be support by other authors/researchers. Reply: The indicators selected in each hypothesis are based on some indicators commonly used by other scholars in the literature. At the same time, they also discuss the relationship between each pair of indicators in the literature. These are included in the literature review and research hypotheses of this article. mentioned. However, no scholar has yet clearly defined the linkage changes between indicators as a signal of whether profits are healthy. Therefore, this is also the research innovation of this article. Not long ago, our team has applied for a patent for the improved research, and it has been approved. - add information about the number of hypotheses in the abstract and the introduction Reply: Based on your suggestion, we have added some descriptions ”this study proposes four hypotheses about identifiers and one hypothesis about the overall model” “Hypotheses of four sub-models and one overall model are proposed.” in the abstract and the introduction - the overarching model hypothesis H - what is a purpose/idea of its formulating? Reply: Hypothesis H is proposed mainly to explain that the four identifiers jointly affect profit health. In this way, the idiosyncratic contribution values of the four pairs of indicators to PH and the correlation between each variable can be analyzed to analyze the impact of each indicator on profit health. At the same time, the four team indicators can be regarded as a whole, reflecting the systematic and comprehensive nature of profit health assessment. The overall model is verified later and this hypothesis is proved. Methodology - a separate section focusing on the methodology is missing - some information are mentioned in the section "Theoretical Framework and Research Hypotheses", other ones in the section "Empirical Research) - from my point of view, the separate section should be created with all information required Reply: Thank you very much for this valuable suggestion. Our research team agrees very much with it and has written a separate chapter to describe the research method. Empirical Research - Sample Selection and Data Collection - identify the number of subjects that are evaluated, describe them Reply: Thank you very much for this valuable suggestion. Our research team agrees very much with it and has added some description like” This study takes private companies listed on the ChiNext board of A-shares in China as the research object and collects financial and non-financial data from 2018 to 2022 from the Wind database. As of December 31, 2018, there were 580 private enterprises listed on the ChiNext board (excluding ST or ST), with a total of 2,900 records. After removing outliers, 2,622 valid records remain. ST and ST companies are removed from the sample set to reduce model testing bias due to sample imbalance. Extreme values of various indicators are also removed. These steps ensure research rigor and result reliability, providing a solid data foundation for in-depth analysis of the financial health of private listed companies on the ChiNext board.” - Variable definitions - identify the units for each variable + add information about the time period evaluated Reply: All the above variables are dimensionless variables. Among them, PH is the score calculated by each recognizer. ARGR, RGR, NCFGR, NPGR, ITR, GPGR, and GRGR are the calculated relevant growth rates. AO is the score assigned according to different audit opinion types. NCAF is the number of times an enterprise changes accounting firms, with one point for each change. This has already described in the article. - Descriptive statistics - the figures should be prepared with better quality, why not all variables are described? Reply: The descriptive statistics in this part mainly explain the relationship between the four pairs of financial indicators and the number of samples whose changing trends are inconsistent, so as to observe the changes of each identifier. The reason why AO and NCAF are not statistically described is because these two indicators are assigned by the type of audit opinion and the number of times the company changes accounting firms. It is a single signal and only affects PH, so it is not included here. describe it. However, in the sub-model test below, it is described by drawing the Partial Dependence Plot of Sub-Model. - Correlation Analysis - the CA should be included in the methodology Reply: The correlation analysis here mainly demonstrates the relationship between various indicators. It is a part of describing the characteristics of the data. It also explains why non-linear regression model methods such as gradient boosting machine and random forest are used to verify the model. It has a link between the past and the future. role. If descriptive statistics have not yet been performed on the data, placing them in the research methods chapter may affect the reader's reading logic. Empirical Results Analysis and Robustness Test - highlight the structure of this section on its beginning Reply: Based on your suggestion, we have added some descriptions “This section primarily pertains to the examination of two categories of models. Firstly, the gradient boosting machine algorithm is employed to test the overall model, thereby validating the combined impact of nine financial and non-financial indicators on profit health (PH). Secondly, the random forest algorithm is utilized to test four sub-models, with the aim of verifying the influence of a single detector on profit health (PH).” - Table 3 - move it as an annex Reply: Based on your suggestion, we have moved it as appendix A Theoretical Application - the title should be changed (the content is different) Reply: the title has been changed as “7.Application and Expansion” Conclusion - add information about the limitations of the research presented Reply: In subsequent research, we also found that performance forecasts, relative market range increases and decreases, and ESG scores are also related to financial health. For example, most ST and ST companies do not have performance forecasts, which shows that these companies have the idea of covering up the problem. These are our follow-up research directions, so there is still room for improvement in the current financial health assessment framework, and more non-financial indicators can be added. We have added a description at the conclusion. Formal - check the journal template Reply: we have checked it Thank you again for your hard work and professional guidance, and we look forward to your further review and suggestions on our revised article. Attachments Attachment Submitted filename: Response to reviewers.docx* https://doi.org/10.1371/journal.pone.0314966.r002
22 Oct 2024 Decision Letter - Levent ÇALLI, Editor PONE-D-24-28763R1Comprehensive Financial Health Assessment Using Advanced Machine Learning Techniques: Evidence based on private companies listed on ChiNextPLOS ONE Dear Dr. Li, Thank you for submitting your manuscript to PLOS ONE. After careful consideration, we feel that it has merit but does not fully meet PLOS ONE’s publication criteria as it currently stands. Therefore, we invite you to submit a revised version of the manuscript that addresses the points raised during the review process. Please submit your revised manuscript by Dec 06 2024 11:59PM. If you will need more time than this to complete your revisions, please reply to this message or contact the journal office at plosone@plos.org. When you're ready to submit your revision, log on to https://www.editorialmanager.com/pone/ and select the 'Submissions Needing Revision' folder to locate your manuscript file. Please include the following items when submitting your revised manuscript: A rebuttal letter that responds to each point raised by the academic editor and reviewer(s). You should upload this letter as a separate file labeled 'Response to Reviewers'. A marked-up copy of your manuscript that highlights changes made to the original version. You should upload this as a separate file labeled 'Revised Manuscript with Track Changes'. An unmarked version of your revised paper without tracked changes. You should upload this as a separate file labeled 'Manuscript'. If you would like to make changes to your financial disclosure, please include your updated statement in your cover letter. Guidelines for resubmitting your figure files are available below the reviewer comments at the end of this letter. If applicable, we recommend that you deposit your laboratory protocols in protocols.io to enhance the reproducibility of your results. Protocols.io assigns your protocol its own identifier (DOI) so that it can be cited independently in the future. For instructions see: https://journals.plos.org/plosone/s/submission-guidelines#loc-laboratory-protocols. Additionally, PLOS ONE offers an option for publishing peer-reviewed Lab Protocol articles, which describe protocols hosted on protocols.io. Read more information on sharing protocols at https://plos.org/protocols?utm_medium=editorial-email&utm_source=authorletters&utm_campaign=protocols. We look forward to receiving your revised manuscript. Kind regards, Levent ÇALLI, Ph.D Academic Editor PLOS ONE Journal Requirements: Please review your reference list to ensure that it is complete and correct. If you have cited papers that have been retracted, please include the rationale for doing so in the manuscript text, or remove these references and replace them with relevant current references. Any changes to the reference list should be mentioned in the rebuttal letter that accompanies your revised manuscript. If you need to cite a retracted article, indicate the article’s retracted status in the References list and also include a citation and full reference for the retraction notice. [Note: HTML markup is below. Please do not edit.] Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation. Reviewer #1: All comments have been addressed Reviewer #2: (No Response) ******** 2. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: Yes Reviewer #2: Yes ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes Reviewer #2: Yes ****** 4. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified. Reviewer #1: Yes Reviewer #2: Yes ****** 5. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here. Reviewer #1: Yes Reviewer #2: Yes ****** 6. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: The authors of the article "Comprehensive Financial Health Assessment Using Advanced Machine Learning Techniques: Evidence based on private companies listed on ChiNext" have seriously revised and improved the article according to the comments of the reviewers. The article can be considered for further steps for publication. Reviewer #2: Dear authors, I am glad I have this opportunity to review your manuscript entitled "Comprehensive Financial Health Assessment Using Advanced Machine Learning Techniques: Evidence based on private companies listed on ChiNext". My comments/notes are as follows (according to my first review): Abstract Note: be more specific and identify the area and/or time period you are focusing on R: Done Note: clearly identify the aim of your study/research R: See the SMART requirements and modify the aim based on them. Note: more focus on the methodology description and add other important information (be more specific) R: Done. Note: findings are too general (model can effectively differentiate....; validity of the proposed framework in practical applications is verified ...) R: Done. Note: explain the acronym "ST" R: Done. I personally prefer to not use this acronym in this section (it looks weird that you have a note there) Introduction Note: what is a research question you are answering on? what is a research gap that will be solved by your research? R: Partially done. Note: add more relevant sources (3 is not enough) R: Done. Note: clearly identify the aim of your study/research R: See the SMART requirements and modify the aim based on them. Note: highlight the structure of your manuscript R: Check other manuscript and prepare appropriate paragraph with the structure description. Theoretical Framework and Research Hypotheses Note: H1, H2 - there are too many variables in one hypothesis and it this was the hypotheses cannot be evaluated correctly (focus on 2 variables for each hypotheses) R: Explained. Note: H1, H2 - how it will be verified? ("...and inconsistent trends in these areas may signal unhealthy profits") R: Explained. Note: H3, H4 - how it will be verified? ("When inconsistent trends are exhibited in these two areas, it may indicate unhealthy profit signals.") R: Explained. Note: each hypothesis should be explained/described using another research results (why you are expecting the relationship between these indicators?) The current description represents your own point of view that should be support by other authors/researchers. R: Explained. Note: add information about the number of hypotheses in the abstract and the introduction R: Done. Note: the overarching model hypothesis H - what is a purpose/idea of its formulating? R: Explained. Methodology Note: a separate section focusing on the methodology is missing; some information are mentioned in the section "Theoretical Framework and Research Hypotheses", other ones in the section "Empirical Research); from my point of view, the separate section should be created with all information required R: Done. Empirical Research Note: Sample Selection and Data Collection - identify the number of subjects that are evaluated, describe them R: Done. Note: Variable definitions - identify the units for each variable + add information about the time period evaluated R: Done. Note: Descriptive statistics - the figures should be prepared with better quality, why not all variables are described? R: Explained. - Correlation Analysis - the CA should be included in the methodology R: Explained. Empirical Results Analysis and Robustness Test Note: highlight the structure of this section on its beginning R: Check other manuscript and prepare appropriate paragraph with the structure description. Note: Table 3 - move it as an annex R: Done. Theoretical Application Note: the title should be changed (the content is different) R: Done. Conclusion Note: add information about the limitations of the research presented R: Done. Formal Note: check the journal template R: Done. ****** 7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy. Reviewer #1: No Reviewer #2: No ******** [NOTE: If reviewer comments were submitted as an attachment file, they will be attached to this email and accessible via the submission site. Please log into your account, locate the manuscript record, and check for the action link "View Attachments". If this link does not appear, there are no attachment files.] While revising your submission, please upload your figure files to the Preflight Analysis and Conversion Engine (PACE) digital diagnostic tool, https://pacev2.apexcovantage.com/. PACE helps ensure that figures meet PLOS requirements. To use PACE, you must first register as a user. Registration is free. Then, login and navigate to the UPLOAD tab, where you will find detailed instructions on how to use the tool. If you encounter any issues or have any questions when using PACE, please email PLOS at figures@plos.org. Please note that Supporting Information files do not need this step. https://doi.org/10.1371/journal.pone.0314966.r003
Revision 2
4 Nov 2024 Author Response Respected reviewers: We express our heartfelt gratitude to you for once again sparing precious time from your hectic schedule to provide valuable comments on this paper. Upon receiving your review remarks, our team has once again carried out comprehensive and painstaking revisions to the paper. The following are our detailed responses to each of your revision suggestions. Abstract Note: be more specific and identify the area and/or time period you are focusing on R: Done Note: clearly identify the aim of your study/research R: See the SMART requirements and modify the aim based on them. Reply: Based on your suggestion, the summary has been revised as follows: Abstract: This study develops a specific and measurable framework for assessing the financial health (FH) of privately-owned companies listed on ChiNext, aimed at identifying financially sound enterprises and helping investors avoid losses caused by financial fraud or earnings management. The research proposes and tests four hypotheses related to key financial indicators and one overarching hypothesis regarding the model’s performance. Using gradient boosting machines and random forests, the model achieves high accuracy and robustness against overfitting through iterative learning. The framework incorporates four pairs of financial indicators and two non-financial indicators into four classifiers, significantly outperforming the Altman Z-score model in predicting financial soundness. Among 75 private companies with special treatment by the Securities Regulatory Commission in Shanghai and Shenzhen in 2022, 72 were correctly identified as sub-healthy or unhealthy, achieving an accuracy rate of 96%. This study demonstrates time-bound practical value by validating the model with 2022 data and highlights its relevance for cross-market applications. The results provide achievable solutions for enterprise managers and policymakers in financial decision-making and risk management. Note: more focus on the methodology description and add other important information (be more specific) R: Done. Note: findings are too general (model can effectively differentiate....; validity of the proposed framework in practical applications is verified ...) R: Done. Note: explain the acronym "ST" R: Done. I personally prefer to not use this acronym in this section (it looks weird that you have a note there) Reply: Based on your feedback, I have removed this acronym and replaced it with the phrase 'with special treatment by the Securities Regulatory Commission' Introduction Note: what is a research question you are answering on? what is a research gap that will be solved by your research? R: Partially done. Reply: According to your feedback, relevant research questions and descriptions of research gaps have been added to the Introduction, as follows: This study addresses the research question: How can machine learning models enhance the effectiveness of profit health assessment by integrating both financial and non-financial indicators? While existing research primarily focuses on financial fraud detection and earnings manipulation, there is a gap in providing comprehensive profit health assessments. The absence of methods combining financial and non-financial indicators limits the ability of investors and stakeholders to quickly and accurately identify companies with healthy financial conditions. To address this gap, this study builds on theories of earnings management, financial distress, and signal transmission to construct a profit health assessment framework. This model aims to overcome the limitations of traditional financial ratios by using a hybrid approach that integrates financial and non-financial data. Note: add more relevant sources (3 is not enough) R: Done. Note: clearly identify the aim of your study/research R: See the SMART requirements and modify the aim based on them. Reply: According to your feedback, the aim has been revised as follows: To address this gap, this study builds on theories of earnings management, financial distress, and signal transmission to construct a profit health assessment framework. This model aims to overcome the limitations of traditional financial ratios by using a hybrid approach that integrates financial and non-financial data. Furthermore, this study endeavours to combine this model with the Z-score model to enhance the effective identification of and ability to classify corporate financial health status [7], which offers an important assessment tool for financial conditions and risks to corporate stakeholders. Note: highlight the structure of your manuscript R: Check other manuscript and prepare appropriate paragraph with the structure description. Reply: According to your feedback, the structure description has been added in the introduction as follows: The article introduces, analyzes empirically, and applies the financial health model through the following chapters: � Introduction: Establishes the context, research questions, and research gap. � Literature Review: Summarizes key theories and previous studies. � Theoretical Framework and Hypotheses: Proposes research hypotheses and conceptual models. � Methodology: Details the research methods and data collection strategies. � Empirical Research: Variable definition and model construction � Empirical Results and Robustness Test: Analyzes the empirical results and ensures their stability. � Aplication and Expansion: Application of profit health evaluation and extend to financial assessment � Conclusion : Highlights the contributions and practical implications of the study. Theoretical Framework and Research Hypotheses Note: H1, H2 - there are too many variables in one hypothesis and it this was the hypotheses cannot be evaluated correctly (focus on 2 variables for each hypotheses) R: Explained. Note: H1, H2 - how it will be verified? ("...and inconsistent trends in these areas may signal unhealthy profits") R: Explained. Note: H3, H4 - how it will be verified? ("When inconsistent trends are exhibited in these two areas, it may indicate unhealthy profit signals.") R: Explained. Note: each hypothesis should be explained/described using another research results (why you are expecting the relationship between these indicators?) The current description represents your own point of view that should be support by other authors/researchers. R: Explained. Note: add information about the number of hypotheses in the abstract and the introduction R: Done. Note: the overarching model hypothesis H - what is a purpose/idea of its formulating? R: Explained. Methodology Note: a separate section focusing on the methodology is missing; some information are mentioned in the section "Theoretical Framework and Research Hypotheses", other ones in the section "Empirical Research); from my point of view, the separate section should be created with all information required R: Done. Empirical Research Note: Sample Selection and Data Collection - identify the number of subjects that are evaluated, describe them R: Done. Note: Variable definitions - identify the units for each variable + add information about the time period evaluated R: Done. Note: Descriptive statistics - the figures should be prepared with better quality, why not all variables are described? R: Explained. - Correlation Analysis - the CA should be included in the methodology R: Explained. Empirical Results Analysis and Robustness Test Note: highlight the structure of this section on its beginning R: Check other manuscript and prepare appropriate paragraph with the structure description. Reply: According to your feedback, the structure description has been added in this section on its beginning as follows: This section primarily pertains to the examination of two categories of models. Firstly, the gradient boosting machine algorithm is employed to test the overall model, thereby validating the combined impact of nine financial and non-financial indicators on profit health (PH). Secondly, the random forest algorithm is utilized to test four sub-models, with the aim of verifying the influence of a single detector on profit health (PH). Note: Table 3 - move it as an annex R: Done. Theoretical Application Note: the title should be changed (the content is different) R: Done. Conclusion Note: add information about the limitations of the research presented R: Done. Formal Note: check the journal template R: Done. Attachments Attachment Submitted filename: Response to reviewers comment.docx https://doi.org/10.1371/journal.pone.0314966.r004
20 Nov 2024 Decision Letter - Levent ÇALLI, Editor Comprehensive Financial Health Assessment Using Advanced Machine Learning Techniques: Evidence based on private companies listed on ChiNext PONE-D-24-28763R2 Dear Dr. Li, We’re pleased to inform you that your manuscript has been judged scientifically suitable for publication and will be formally accepted for publication once it meets all outstanding technical requirements. Within one week, you’ll receive an e-mail detailing the required amendments. When these have been addressed, you’ll receive a formal acceptance letter and your manuscript will be scheduled for publication. An invoice will be generated when your article is formally accepted. Please note, if your institution has a publishing partnership with PLOS and your article meets the relevant criteria, all or part of your publication costs will be covered. Please make sure your user information is up-to-date by logging into Editorial Manager at Editorial Manager® and clicking the ‘Update My Information' link at the top of the page. If you have any questions relating to publication charges, please contact our Author Billing department directly at authorbilling@plos.org. If your institution or institutions have a press office, please notify them about your upcoming paper to help maximize its impact. If they’ll be preparing press materials, please inform our press team as soon as possible -- no later than 48 hours after receiving the formal acceptance. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org. Kind regards, Levent ÇALLI, Ph.D Academic Editor PLOS ONE Additional Editor Comments (optional): Reviewers' comments: Reviewer's Responses to Questions Comments to the Author 1. If the authors have adequately addressed your comments raised in a previous round of review and you feel that this manuscript is now acceptable for publication, you may indicate that here to bypass the “Comments to the Author” section, enter your conflict of interest statement in the “Confidential to Editor” section, and submit your "Accept" recommendation. Reviewer #1: All comments have been addressed Reviewer #2: All comments have been addressed ******** 2. Is the manuscript technically sound, and do the data support the conclusions? The manuscript must describe a technically sound piece of scientific research with data that supports the conclusions. Experiments must have been conducted rigorously, with appropriate controls, replication, and sample sizes. The conclusions must be drawn appropriately based on the data presented. Reviewer #1: Yes Reviewer #2: Yes ****** 3. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes Reviewer #2: Yes ****** 4. Have the authors made all data underlying the findings in their manuscript fully available? The PLOS Data policy requires authors to make all data underlying the findings described in their manuscript fully available without restriction, with rare exception (please refer to the Data Availability Statement in the manuscript PDF file). The data should be provided as part of the manuscript or its supporting information, or deposited to a public repository. For example, in addition to summary statistics, the data points behind means, medians and variance measures should be available. If there are restrictions on publicly sharing data—e.g. participant privacy or use of data from a third party—those must be specified. Reviewer #1: Yes Reviewer #2: Yes ****** 5. Is the manuscript presented in an intelligible fashion and written in standard English? PLOS ONE does not copyedit accepted manuscripts, so the language in submitted articles must be clear, correct, and unambiguous. Any typographical or grammatical errors should be corrected at revision, so please note any specific errors here. Reviewer #1: Yes Reviewer #2: Yes ****** 6. Review Comments to the Author Please use the space provided to explain your answers to the questions above. You may also include additional comments for the author, including concerns about dual publication, research ethics, or publication ethics. (Please upload your review as an attachment if it exceeds 20,000 characters) Reviewer #1: The authors of the article "Comprehensive Financial Health Assessment Using Advanced Machine Learning Techniques: Evidence based on private companies listed on ChiNext?" have seriously revised, supplemented and explained the comments of the reviewers. The article can be considered for publication. Reviewer #2: Thanks for time you spent incorporating my comments/notes. I wish you all the best with this manuscript and other ones in the future. ****** 7. PLOS authors have the option to publish the peer review history of their article (what does this mean?). If published, this will include your full peer review and any attached files. If you choose “no”, your identity will remain anonymous but your review may still be made public. Do you want your identity to be public for this peer review? For information about this choice, including consent withdrawal, please see our Privacy Policy. Reviewer #1: No Reviewer #2: No ******** https://doi.org/10.1371/journal.pone.0314966.r005
Formally Accepted
2 Dec 2024 Acceptance Letter - Levent ÇALLI, Editor PONE-D-24-28763R2 PLOS ONE Dear Dr. Li, I'm pleased to inform you that your manuscript has been deemed suitable for publication in PLOS ONE. Congratulations! Your manuscript is now being handed over to our production team. At this stage, our production department will prepare your paper for publication. This includes ensuring the following: * All references, tables, and figures are properly cited * All relevant supporting information is included in the manuscript submission, * There are no issues that prevent the paper from being properly typeset If revisions are needed, the production department will contact you directly to resolve them. If no revisions are needed, you will receive an email when the publication date has been set. At this time, we do not offer pre-publication proofs to authors during production of the accepted work. Please keep in mind that we are working through a large volume of accepted articles, so please give us a few weeks to review your paper and let you know the next and final steps. Lastly, if your institution or institutions have a press office, please let them know about your upcoming paper now to help maximize its impact. If they'll be preparing press materials, please inform our press team within the next 48 hours. Your manuscript will remain under strict press embargo until 2 pm Eastern Time on the date of publication. For more information, please contact onepress@plos.org. If we can help with anything else, please email us at customercare@plos.org. Thank you for submitting your work to PLOS ONE and supporting open access. Kind regards, PLOS ONE Editorial Office Staff on behalf of Assoc. Prof. Levent ÇALLI Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0314966.r006

Open letter on the publication of peer review reports

PLOS recognizes the benefits of transparency in the peer review process. Therefore, we enable the publication of all of the content of peer review and author responses alongside final, published articles. Reviewers remain anonymous, unless they choose to reveal their names.

We encourage other journals to join us in this initiative. We hope that our action inspires the community, including researchers, research funders, and research institutions, to recognize the benefits of published peer review reports for all parts of the research system.

Learn more at ASAPbio .