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.
I confirm that you addressed all the reviewer's comments.
M.P.
[# PeerJ Staff Note - this decision was reviewed and approved by Jyotismita Chaki, a 'PeerJ Computer Science' Section Editor covering this Section #]
All comments have been added in detail to the last section.
All comments have been added in detail to the last section.
All comments have been added in detail to the last section.
Thank you for the revision. All referee comments have been adequately responded to. Since the paper has the potential to make an important contribution to the literature in its current form, I recommend that it be accepted. I wish the authors success in their future work. Best regards.
Dear Authors,
I have carefully read your answer to the comment raised by Reviewer#2.
You are right in sayin that the dataset details are not the central point of your work. Nonetheless, I think that the you should address comment #6 in a proper way.
For example you should add a couple of columns in the table: one with the link to the repo where the dataset is and the second one reporting the metric (and its value) used for evaluating the model ( given that in RQ6 you ask what metrics are used to evaluate the performance of models.)
All comments are in the last section.
All comments are in the last section.
All comments are in the last section.
Review Report for PeerJ Computer Science
(Analyzing the critical steps in deep learning-based stock forecasting: A systematic literature review)
Thanks for the revision. The responses to the reviewer comments and the relevant changes/additions to the paper have been examined in detail. Some of the responses to the first reviewer comments are sufficient, some are limited, and some are insufficient. The limited ones are still at an acceptable level. However, the comment that the information requested in the sixth item at the first stage was considered "unnecessary" and was not added is an inappropriate and insufficient response. For the paper to contribute fully to the literature and increase its potential for citations after publication, it must complete the first revision requests.
Dear Authors,
I agree with the comments provided by the reviewers.
Please, follow carefully the suggestions given by the reviewers and address all the comments. In particular pay attention to the very interesting comments provided reviewer #2 .
The review is of broad and cross-disciplinary interest, making it highly relevant to a diverse readership. It fits seamlessly within the scope of the journal, offering insights that will engage readers from various fields and foster interdisciplinary dialogue.
Even though the field has been reviewed recently, this review stands out by providing a unique perspective that justifies its publication. It approaches the topic from a different angle and is tailored to be accessible to a wider or different audience, thereby adding significant value to the existing body of literature.
The Introduction is well-crafted, effectively setting the stage for the review. It clearly introduces the subject matter and articulates the motivation behind the review, making it evident who the intended audience is. This clarity ensures that readers understand the relevance and importance of the research from the very beginning.
The approach is thorough and systematic, ensuring that all relevant aspects of the topic are addressed. This comprehensive methodology enhances the credibility and reliability of the review.
Sources are cited meticulously throughout the review, ensuring that all referenced material is properly acknowledged. The balance between direct quotations and paraphrasing is handled with skill, adding depth to the discussion while maintaining originality and clarity.
The review is organized in a highly logical and coherent manner, with well-structured paragraphs and subsections. This clear organization facilitates easy navigation and comprehension, allowing readers to follow the progression of ideas seamlessly. Each section builds on the previous one, contributing to a cohesive and engaging narrative.
The article presents a well-developed and convincingly supported argument that effectively meets the goals outlined in the Introduction. The logical progression of ideas and the robust evidence provided throughout the review ensure that the initial objectives are thoroughly addressed and accomplished.
The Conclusion is particularly strong, as it thoughtfully identifies unresolved questions and gaps in the current research. It also outlines future directions, providing valuable guidance for subsequent studies. This forward-looking perspective enhances the review's contribution to the field by suggesting avenues for further exploration and development.
All comments have been added in detail to the last section.
All comments have been added in detail to the last section.
All comments have been added in detail to the last section.
Review Report for PeerJ Computer Science
(Analyzing the critical steps in deep learning-based stock forecasting: A systematic literature review)
1. Within the scope of the study, stock forecasting studies conducted using various deep learning methods in the literature were examined in detail.
2. In the introduction section, what stock forecasting is, the approach of stock forecasting models in recent years, and sections such as feature selection and performance evaluation are mentioned. In this section, both the importance of the subject and the purpose of the study are clearly stated.
3. The 6 questions in the Research Strategy section are sufficient in terms of content and approach. It is stated that the focus is on q1 and q2 studies in the last 5 years. The databases used are specified as Scopus, WoS and IEEE Xplore. When we look at the selected databases, IEEE publisher publications are mainly available in IEEE Xplore, all publishers (including IEEE) can access SCIE indexed publications in WoS, and many publishers' publications with CiteScore can be found in Scopus. IEEE publications are also available in WoS and Scopus. For this reason, explain the reasons why IEEE Xplore was kept separate and other publishers (Wiley, Springer, Taylor and Francis) were not selected for such a search.
4. When multidisciplinary artificial intelligence studies in the literature, including stock forecasting studies within the scope of the study, are examined, the importance of open access publications and publishers is increasing. For this reason, analyze the articles examined within the scope of the study in more detail in terms of open access. Also, analyze in more detail in terms of WoS Categories where the journals specified as q1 and q2 are selected.
5. For the publications dated 2023 and 2024, check the quartiles of the journals in which the articles examined were published according to the new JCR 2023 announced by Clarivate on June 20. Also, include the new q1 and q2 articles in the literature.
6. For the studies in Table-4, include dataset details, metric results, github etc. code links.
As a result, although the study conducts an important literature review in terms of the subject discussed, it is recommended to pay attention to the sections listed above.
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.