All reviews of published articles are made public. This includes manuscript files, peer review comments, author rebuttals and revised materials. Note: This was optional for articles submitted before 13 February 2023.
Peer reviewers are encouraged (but not required) to provide their names to the authors when submitting their peer review. If they agree to provide their name, then their personal profile page will reflect a public acknowledgment that they performed a review (even if the article is rejected). If the article is accepted, then reviewers who provided their name will be associated with the article itself.
Dear authors, we are pleased to verify that you meet the reviewer's valuable feedback to improve your research.
Thank you for considering PeerJ Computer Science and submitting your work.
Kind regards
PCoelho
[# PeerJ Staff Note - this decision was reviewed and approved by Mehmet Cunkas, a PeerJ Section Editor covering this Section #]
no comment
no comment
no comment
Figure 5 could be easily resized to take less space without losing its intent.
The authors have addressed my comments
The authors have addressed my comments
The authors have addressed my comments
The authors have addressed my comments
Dear authors,
Thanks a lot for your manuscript.
Please address the issues relating to model selection justification and claims of real-world applicability. Additionally, the comparison with existing methods is limited while some sections are overly detailed, affecting readability. A streamlined presentation and clearer results would enhance the paper’s quality.
Kind regards,
PCoelho
[# PeerJ Staff Note: The review process has identified that the English language must be improved. PeerJ can provide language editing services if you wish - please contact us at [email protected] for pricing (be sure to provide your manuscript number and title). Your revision deadline is always extended while you undergo language editing. #]
This work proposes an Ethereum blockchain enhancement through an ensemble approach to detect fraud upon generating the transaction stored in the blockchain.
Clear and unambiguously written. Although it is a lengthy article.
Found a couple of typos (eg., 173 - Random, 603 - exponential, 605 - these, 609 - was, 610 - were, 614 - and, 616 - while, 620 - integration )
Introduction and Related Work are relevant and demonstrate context. References are well-referenced and are relevant despite being easier to read with another bibliographical notation (IEEE Numerical Reference System).
The article falls within the context of the journal and provides enough information in its main text and also in supplementary materials that promote transparency and enough information to replicate the experiment.
The method is fully described and each stage is documented.
The amount of references is adequate but the authors present a blockchain introduction, specifically to Bitcoin and Ethereum, thus, consider the following 2 references:
- Nakamoto, S. (2008). Bitcoin: A peer-to-peer electronic cash system.
- Buterin, V. (2013). Ethereum white paper. GitHub repository, 1, 22-23.
**PeerJ Staff Note:** It is PeerJ policy that additional references suggested during the peer-review process should only be included if the authors are in agreement that they are relevant and useful.
No comment.
This work needs only a final proofreading.
It is a detailed work with full supplementary materials that allow researchers to completely replicate the experiment.
I congratulate the authors on the work accomplished and the best for the upcoming steps in this line of work.
Paper is well structured.
Experimetal results are acceptable.
Good
NA
The paper is valuable but requires significant revisions for clarity, real-world validation, and a stronger comparison with existing methods.
The paper uses clear and professional language. However, some sections, particularly the introduction and results, are overly detailed. These could be streamlined for conciseness.
The background and literature review are comprehensive, but the paper could benefit from a clearer focus on how it builds upon past work.
The overall structure conforms to PeerJ standards, though better transitions between sections would improve flow.
The methodology is well-described, with sufficient detail for reproducibility. However, more explanation is needed for the model selection process, especially why specific ensemble models were chosen.
Data preprocessing steps are thorough, but more information is required on handling imbalanced data, especially with respect to fraudulent transactions.
While the evaluation metrics are clear, the reasoning behind choosing certain metrics should be elaborated further.
The results are promising, particularly the accuracy of over 98%. However, the paper should present more comparison with state-of-the-art models in fraud detection on blockchain platforms.
The paper claims real-world usage, but this could be substantiated further with examples of how the system might operate in practice.
The figures are well-presented but could benefit from more descriptive captions, explaining their relevance to the results.
The dataset source is well-cited, but additional discussion on data limitations (e.g., bias or missing data) is needed.
All text and materials provided via this peer-review history page are made available under a Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.