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, congratulations! The reviewers are satisfied with your revisions and recommended an accept decision. Please fully proofread the paper before submitting the production related copy.
[# PeerJ Staff Note - this decision was reviewed and approved by Stefan Wagner, a 'PeerJ Computer Science' Section Editor covering this Section #]
All figures are missing from the attached file. Others look good to me.
My previous feedback has been addressed, and everything looks good now.
My previous feedback has been addressed, and everything looks good now.
N/A
Comments have been implemented. The paper is improved and accepted now.
Comments have been implemented. The paper is improved and accepted now.
Comments have been implemented. The paper is improved and accepted now.
Comments have been implemented. The paper is improved and accepted now.
Accepted
Accepted
Accepted
Accepted
Please see the attached comments from the reviewers. You may address all the comments and re-submit the manuscript for further considerations please.
[# PeerJ Staff Note: The review process has identified that the English language could 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. #]
1. The literature review could be expanded to include studies on the application of machine learning techniques in the auction market. The paper discusses various methods, but it would be beneficial to understand how these methods have already been implemented and their effectiveness in the field.
2. Some sections could benefit from further clarification to ensure the analysis is well performed, such as the data preprocessing steps.
3. The font style is not consistent throughout the paper. It can be fixed for better readability.
3. The figures and tables could be better labeled and described. For example, figure 1 is a bit confusing since it has some text that is not mentioned in the paper.
1. The methodology is described in detail, but some parts need more elaboration. For example, the specific parameters and configurations used in the experiments should be clearly stated.
1. The paper should discuss the potential limitations of the proposed method and suggest areas for future research, which is missing from the paper.
See below
See below
See below
The paper provides a clear overview of the topic— Adaptive Learning Algorithm Based Price Prediction Model for Auction Lots. It highlights the significance of constructing an auction item price prediction model based on an adaptive learning algorithm. To enhance the clarity and impact of the paper , consider the following suggestions to incorporate:
Basic:
1-Authors are required to initially use full forms. Such as Kalman Filter, Long Short-Term Memory, Double Clustering, Dynamic Time Warping etc. After using full forms authors can utilize their short forms or abbreviations.
2-The abstract should be more elaborative, including the introduction, problem statement, methodology, results, etc.
3-Explicitly state the current challenges or gaps in existing prediction models that your proposed approach aims to address.
4-There exist some grammatical errors in text i.e in line 318 the “data” is plural so there should be “undergo” instead of “undergoes”. Similarly, place “the” before model names such as in line no. 378 and 382. The authors should reconsider the text of research article.
5-Try to avoid using “To” for starting a sentence in research papers. Line 332, 342 etc.
Methodology:
6-The size of dataset is important while training the deep learning models. Therefore, authors are suggested to mention the size of dataset explicitly.
7-Elaborate briefly the appropriate reason behind using the Kalman Filter with LSTM model.
8-Discuss the parameters used in proposed model such as state transition matrix, measurement matrix in Kalman Filter and number of layers, number of units, activation function, learning rate, number of epochs in LSTM model.
9-The results were compared with (DC(POWER-NWP)-CNN and DC(DWT-NWP)-CNN), however, there is need to mention why these models were selected for comparison.
Validity of Findings:
10-Please clarify which features were the most important in predicting the auction prices.
11-Achieving 90.23 accuracy raises over-fitting concern. Authors didn’t mention any validation set for training. Therefore, model should be tested on some other dataset.
12-Please discuss the limitations of the proposed study.
No comments.
Not sufficient.
Not found significant.
1. The concept of Adaptive learning which the author claims in the article need to be presented in a better and formal way. It is bit confusing.
2. The equations need to be formatted properly.
3. Please follow an algorithmic approach to present all the algorithms.
4. Please format Eq. 16-18.
5. The Conclusion and Abstract section must be rewritten in a better way to show the unique outcome/contribution of the proposed models.
6. The comparative studies is not significant to claim the superiority of the proposed approach.
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.