Predicting stock returns using machine learning combined with data envelopment analysis and automatic feature engineering: A case study on the Vietnamese stock market

Hoang Thanh Nhon; Nga Do-Thi; Thao Nguyen-Trang

doi:10.1371/journal.pone.0332154

Peer Review History

Original SubmissionJune 16, 2025
2 Jul 2025 Decision Letter - Miguel Alves Pereira, Editor PONE-D-25-32672Predicting stock returns using machine learning combined with data envelopment analysis and automatic feature engineering: A case study on the Vietnamese stock marketPLOS ONE Dear Dr. Nguyen-Trang, 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 Aug 16 2025 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, Miguel Alves Pereira Academic Editor PLOS ONE Journal Requirements: When submitting your revision, we need you to address these additional requirements. 1. 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. In the online submission form, you indicated that “The data used in this study are available upon request. If you require access to the data, please contact the corresponding author.” All PLOS journals now require all data underlying the findings described in their manuscript to be freely available to other researchers, either 1. In a public repository, 2. Within the manuscript itself, or 3. Uploaded as supplementary information. This policy applies to all data except where public deposition would breach compliance with the protocol approved by your research ethics board. If your data cannot be made publicly available for ethical or legal reasons (e.g., public availability would compromise patient privacy), please explain your reasons on resubmission and your exemption request will be escalated for approval. 3. 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. Additional Editor Comments: The manuscript presents a methodologically sound and potentially valuable contribution to the intersection of efficiency analysis and machine learning for stock return prediction in emerging markets. However, the manuscript requires further refinement to meet publication standards. Specifically, the abstract and conclusion fail to adequately convey the study’s impact, and the presentation of results (particularly in terms of model comparisons and hyperparameter settings) lacks the transparency necessary for reproducibility. The limitations of the study, especially the small and sector-specific sample, must be explicitly acknowledged. Figures should be revised to better reflect the proposed approach, and concrete examples of feature engineering outputs would improve clarity. [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: Partly ******** 2. Has the statistical analysis been performed appropriately and rigorously? Reviewer #1: Yes Reviewer #2: No ****** 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: No ****** 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 manuscript titled "Predicting stock returns using machine learning combined with data envelopment analysis and automatic feature engineering: A case study on the Vietnamese stock market" presents an original and well-structured approach to stock return prediction in an emerging market. Its main contribution lies in the use of efficiency scores derived from Data Envelopment Analysis (DEA) as explanatory variables within machine learning models — a technique still underexplored in financial prediction literature. The manuscript is technically sound, with a solid methodology and appropriate validation via 3-fold cross-validation. The authors applied various machine learning models (GLM, DANN, SVR, Random Forest, and GBT), with hyperparameter tuning conducted via grid search. The inclusion of automatic feature engineering further enhances the study, revealing significant improvements in error metrics (RMSE, MAE, MAPE). Strengths - Originality: The integration of DEA efficiency scores is novel, especially in the context of the Vietnamese stock market. - Robust methodology: Combining technical, fundamental, and efficiency variables with automated feature engineering strengthens model performance. - Practical relevance: Focusing on an emerging market with low liquidity and political sensitivity adds value for local analysts and investors. - Clarity: The manuscript is well organized, and the modeling steps are clearly explained. Points for Improvement - Limitations discussion: The authors are encouraged to include a specific section discussing the study's limitations, such as the small sample (26 real estate firms) and the idiosyncrasies of the Vietnamese market. - Feature engineering details: The general explanation is appropriate, but a concrete example of a transformed variable or a table of generated features would enhance clarity. - Additional visualizations: Graphs comparing predicted vs. actual returns would help readers assess the model's real-world performance. - Data availability: While the authors state that data are fully available, providing a direct link to a public repository would improve transparency. Reviewer #2: The paper addresses a good research gap, but due to presentation it lacks the required amount of impact. 1. Abstract does not provided impactive idea regarding the final result. A little summary regarding results will be helpful. 2. Introduction may be shortened and made more technical, a good part of it may be transferred to literature review. 3. A summary of contribution of the paper in listed manner may be added. Paragraph-wise explanation is good, but a summary list will help the reader to understand the paper's content most effectively. 4. Though it is told where to find data, either providing a repository containing it, or giving some lead on how to re-generate it will help future researchers to explore your idea more. Try adding links and guidelines to data procurement or generation more elaboratively. 5. Figures (Diagrams) should be improved to make everything look visually more sound. Figure 3 is just a general diagram of how machine learning works, there is not much to relate to specific proposed model. 6. Comparison between results from different models should be presented more informatively. Hyperparameters could be shown more systematically. Overall, recreating the results of the paper will help future researches generated from it. So more information regarding models and parameters should be added. 7. Conclusion (just like abstract) does hold the full impact of the work. It should be re-written to be more concise and informative regrading the work done. ****** 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: Yes: Tashreef Muhammad ******** [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.0332154.r001
Revision 1
18 Aug 2025 Author Response Authors’ Responses to Reviewers Firstly, we deeply appreciate the advice and encouragement from the Editors and the Reviewers. We thank the Reviewers for their careful evaluation of the manuscript. We have revised the paper with respect to the Reviewer’s comments. We hope that our revised paper will meet the Reviewers’ requirements. The point-by-point responses to the Editors’ and Reviewers’ comments can be found below. It should be noted that the revision is illustrated by the blue color in the revised manuscript. Additional Editor Comments: The manuscript presents a methodologically sound and potentially valuable contribution to the intersection of efficiency analysis and machine learning for stock return prediction in emerging markets. However, the manuscript requires further refinement to meet publication standards. Specifically, the abstract and conclusion fail to adequately convey the study’s impact, and the presentation of results (particularly in terms of model comparisons and hyperparameter settings) lacks the transparency necessary for reproducibility. The limitations of the study, especially the small and sector-specific sample, must be explicitly acknowledged. Figures should be revised to better reflect the proposed approach, and concrete examples of feature engineering outputs would improve clarity. Response: Yes, thank you for the Editors' comments. In the revised manuscript, we have discussed the study's limitations in the conclusion. Additionally, we have clarified the methodology by adding new paragraphs related to feature engineering operators and the search space of parameters. The data and code have also been provided via links. Furthermore, the abstract and conclusion have been revised to better highlight the impacts and results of the study. Finally, the English has been double-checked and corrected. For detailed information, please refer to our responses to the specific comments from the Reviewers below. Reviewer #1 Comments - Limitations discussion: The authors are encouraged to include a specific section discussing the study's limitations, such as the small sample (26 real estate firms) and the idiosyncrasies of the Vietnamese market. Response: Yes, thank you for the Reviewer’s comment. We fully agree that the current paper has some limitations: the sample data is small, and the Vietnamese stock market is idiosyncratic. We have added the following discussion to the conclusion section. Firstly, the proposed method is used in predicting the return of real estate companies listed on the Ho Chi Minh Stock Exchange. This could reduce the generalizability of results to other sectors or broader markets. Therefore, findings derived from this sample may not reflect the behavior or return patterns of firms in manufacturing, technology, or services. The narrow dataset also limits the statistical power of machine learning models and increases the risk of model overfitting, particularly when using complex algorithms. Additionally, the Vietnamese market is young and developing, with low liquidity compared to mature markets. It is strongly influenced by seasonal factors. For example, the Lunar New Year could affect investors’ sentiment and trading volumes, especially in the first quarter. Therefore, this unique characteristic might reduce the transferability of machine learning models trained in different contexts. The corresponding changes can be found in the revised manuscript, lines 387-399. - Feature engineering details: The general explanation is appropriate, but a concrete example of a transformed variable or a table of generated features would enhance clarity. Response: Yes, in response to the Reviewer’s comments, we have included further details of the functions used. The corresponding changes can be seen in the revised manuscript, line 241, and in the new Table 2. - Additional visualizations: Graphs comparing predicted vs. actual returns would help readers assess the model's real-world performance. Response: Yes. We appreciate the Reviewer’s comment. We have added a new figure to depict the scatter plot of actual and predicted returns using F-DEA-GBT. As shown in the new Fig. 4 in the revised manuscript, the actual returns exhibit a positive correlation with the predicted returns. Higher predicted returns correspond to higher actual returns occurring subsequently. The specific value for the correlation coefficient in this case is 0.422. In our opinion, this value is acceptable for issues related to the financial domain, which often involve significant uncertainty. The corresponding changes can be found in the revised manuscript, specifically in the new Fig. 4 and lines 320-325. - Data availability: While the authors state that data are fully available, providing a direct link to a public repository would improve transparency. Response: Yes, thank you for the Reviewer’s comment. For reference, we have published the detailed dataset at the following link: “https://www.kaggle.com/datasets/thaonguyentrang/vietnam-stock-returns-with-efficiency-scores-dea”. The corresponding changes can be found in the revised manuscript, from line 143 to line 146. Reviewer #2 Comments 1. Abstract does not provided impactive idea regarding the final result. A little summary regarding results will be helpful. Response: Yes. We appreciate the Reviewer’s comments. We have added a new paragraph to the abstract: “The results indicate that incorporating business efficiency scores significantly enhances the models' accuracy. For example, the deep neural network model shows a decrease in RMSE from 0.926 to 0.375, MAE from 0.337 to 0.196, and MAPE from 134.63 to 114.71. Furthermore, the gradient boosted tree model, when combined with business efficiency scores and automatic feature engineering, achieves the best results, yielding an MAE of 0.122 and a MAPE of 103.19”. 2. Introduction may be shortened and made more technical, a good part of it may be transferred to literature review. Response: We appreciate the Reviewer’s comments. We have restructured the introduction and literature review sections for improved coherence. Additionally, the language has been refined for greater technical precision. Detailed revisions can be found in the revised manuscript, specifically on lines 1-26 and 34-130. 3. A summary of contribution of the paper in listed manner may be added. Paragraph-wise explanation is good, but a summary list will help the reader to understand the paper's content most effectively. Response: Yes. Thanks for the Reviewer’s comments. We have included a paragraph summarizing the paper’s contributions. Particularly, - This paper is one of the first studies that considers the efficiency score calculated by DEA as a predictor for stock return prediction. - This paper pioneers the application of automatic feature engineering to explore latent and essential predictors related to the efficiency score and other variables, thereby enhancing the model's performance. - This paper serves as a useful reference for selecting an appropriate machine learning model to predict stock returns in the Vietnamese market based on the efficiency score. The corresponding changes can be seen in the revised manuscript, lines 19-26. 4.Though it is told where to find data, either providing a repository containing it, or giving some lead on how to re-generate it will help future researchers to explore your idea more. Try adding links and guidelines to data procurement or generation more elaboratively. Response: Yes, thank you for the Reviewer’s comment. For reference, we have published the detailed dataset at the following link: “https://www.kaggle.com/datasets/thaonguyentrang/vietnam-stock-returns-with-efficiency-scores-dea”. The corresponding changes can be found in the revised manuscript, from line 143 to line 146. 5. Figures (Diagrams) should be improved to make everything look visually more sound. Figure 3 is just a general diagram of how machine learning works, there is not much to relate to specific proposed model. Response: Yes, thank you for the Reviewer’s comment. We have revised the flowchart in Fig. 3 to better reflect the main idea of the proposed algorithm. Please refer to the updated Fig. 3 in the revised manuscript. 6. Comparison between results from different models should be presented more informatively. Hyperparameters could be shown more systematically. Overall, recreating the results of the paper will help future researches generated from it. So more information regarding models and parameters should be added. Response: Yes. In the revised manuscript, we have added paragraphs related to automatic feature engineering, hyper-parameter tuning, and a link to the Python code. The details are as follows. �We have introduced a new Table 2 to clarify the operators used in the automatic feature engineering process. �Additionally, we have specified the search space for the hyper-parameters of the models used. Specifically, for tuning the hyper-parameters of the used models, we perform the grid search optimization in Altair AI Studio to maximize the correlation index between the predicted results and the actual outcomes across the three folds. For each model, we select key hyper-parameters to optimize while keeping the others at their default values. The investigated ranges and steps for the tuned parameters are as follows: oGLM: lambda ranges from 0.0 to 1 with a step of 0.1. oDANN: learning rate ranges from 0.01 to 1 with a step of 0.1. oGBT: max-depth ranges from 1 to 10 with a step of 1; oSVR: C ranges from 0 to 1000 with a step of 100; gamma ranges from 0 to 1 with a step of 0.5; oDT: m ranges from 1 to 10 with a step of 1. �We have provided a link containing the Python code for the best model to ensure repeatability: https://www.kaggle.com/code/thaonguyentrang/lgbm-feature-engineering-for-return-prediction The corresponding changes can be found in the revised manuscript, lines 282-292, 331-334, the new Table 2, and Table 3. 7. Conclusion (just like abstract) does hold the full impact of the work. It should be re-written to be more concise and informative regrading the work done. Response: Yes. We appreciate the Reviewer’s comments. We have rewritten the conclusion to better reflect the results and impact of the study: “This paper has demonstrated that integrating DEA scores with automatic feature engineering significantly enhances prediction accuracy. Among the models tested, the F-DEA-GBT model, which combines DEA-based features with the Gradient Boosted Tree algorithm, achieved the best overall performance. From an academic perspective, the study offers several notable contributions. It is among the first to incorporate DEA efficiency scores into stock return prediction and to apply automatic feature engineering to panel data. These findings extend the current body of knowledge on emerging markets like Vietnam by demonstrating the value of efficiency-based indicators and advanced machine learning techniques in improving forecast accuracy. However, the current paper has some limitations: the sample data is small, and the Vietnamese Stock Market is idiosyncratic. Focusing solely on 26 real estate companies listed on the Ho Chi Minh Stock Exchange reduces the generalizability of results to other sectors or broader markets. Therefore, findings derived from this sample may not reflect the behavior or return patterns of firms in manufacturing, technology, or services. The narrow dataset also limits the statistical power of machine learning models and increases the risk of model overfitting, particularly when using complex algorithms. Additionally, the Vietnamese market is young and developing, with low liquidity compared to mature markets. It is strongly influenced by seasonal factors, such as the Lunar New Year, which affects investor sentiment and trading volumes, especially in the first quarter. Therefore, this unique characteristic reduces the transferability of machine learning models trained in other contexts. Future research can build on these findings by exploring additional variables and incorporating broader datasets to further refine predictive accuracy in diverse market contexts”. The corresponding changes can be seen in the revised manuscript, lines 379-399. Attachments Attachment Submitted filename: rebuttal_letter.docx https://doi.org/10.1371/journal.pone.0332154.r002
27 Aug 2025 Decision Letter - Miguel Alves Pereira, Editor Predicting stock returns using machine learning combined with data envelopment analysis and automatic feature engineering: A case study on the Vietnamese stock market PONE-D-25-32672R1 Dear Dr. Nguyen-Trang, 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. For questions related to billing, please contact billing support. 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, Miguel Alves Pereira 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 #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 #2: Yes ****** 3. Has the statistical analysis been performed appropriately and rigorously? 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 #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 #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 #2: I think the authors did a good job addressing the issues as enlisted. A little suggestion from me will be to include the links of kaggle as footnotes rather than writing them as text in the main body of the paper. ****** 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 #2: Yes: Tashreef Muhammad ******** https://doi.org/10.1371/journal.pone.0332154.r003
Formally Accepted
Acceptance Letter - Miguel Alves Pereira, Editor PONE-D-25-32672R1 PLOS ONE Dear Dr. Nguyen-Trang, 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 You will receive further instructions from the production team, including instructions on how to review your proof when it is ready. Please keep in mind that we are working through a large volume of accepted articles, so please give us a few days 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. You will receive an invoice from PLOS for your publication fee after your manuscript has reached the completed accept phase. If you receive an email requesting payment before acceptance or for any other service, this may be a phishing scheme. Learn how to identify phishing emails and protect your accounts at https://explore.plos.org/phishing. 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 Prof. Miguel Alves Pereira Academic Editor PLOS ONE https://doi.org/10.1371/journal.pone.0332154.r004

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 .