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.
Based on the review of the revisions and the authors’ detailed responses, all of the reviewers’ comments have been fully addressed. The manuscript has been substantially improved in clarity, rigor, and overall presentation. In my view, it is now ready for publication.
[# PeerJ Staff Note - this decision was reviewed and approved by Claudio Ardagna, a PeerJ Section Editor covering this Section #]
All my comments have been thoroughly addressed. It is acceptable in the present form.
All my comments have been thoroughly addressed. It is acceptable in the present form.
All my comments have been thoroughly addressed. It is acceptable in the present form.
This paper adheres to the fundamental standards of scientific reporting, ensuring clarity, structure, and reproducibility. The manuscript is well-organized, following the standard format of PeerJ Computer Science, including an abstract, introduction, methodology, results, discussion, and conclusion.
The literature review is comprehensive and provides a well-structured background on data asset valuation, positioning the proposed SLPDBO-BP model within existing research. Relevant studies are cited appropriately, and all references follow the required format.
The figures and tables included in the manuscript are well-labeled, properly referenced, and contribute to a clear understanding of the results. The text is written in professional, clear, and grammatically correct English, ensuring accessibility to a broad audience.
Additionally, the dataset, algorithms, and experimental results are sufficiently detailed to allow for verification and replication. Any assumptions and limitations of the study are explicitly discussed to maintain transparency.
This manuscript meets the journal's criteria for basic reporting and contributes a novel, well-documented approach to data asset valuation.
The experimental design of this study follows a rigorous and well-structured methodology to validate the effectiveness of the SLPDBO-BP model for data asset valuation. The study is designed to ensure repeatability, reliability, and scientific rigor in evaluating the proposed approach.
Research Objectives
The primary objective of this study is to develop and validate an efficient valuation model for data assets using the SLPDBO-BP framework. The research aims to:
Improve the accuracy of data asset valuation by integrating statistical learning and optimization techniques.
Compare the performance of SLPDBO-BP against existing valuation models.
Analyze the impact of key parameters on valuation accuracy and efficiency.
Methodology
The study employs a quantitative research approach, utilizing both theoretical modeling and empirical evaluation. The key steps in the experimental design include:
Dataset Selection: The experiment uses real-world and synthetic datasets that represent diverse data assets across various domains. The dataset characteristics, including volume, variety, and value parameters, are described in detail to ensure transparency.
Model Implementation: The SLPDBO-BP model is developed and implemented using appropriate computational frameworks. Key hyperparameters are defined, and the model is optimized for performance.
Baseline Comparison: The proposed model is benchmarked against existing data asset valuation models to evaluate improvements in accuracy, efficiency, and computational cost.
Performance Metrics: The evaluation is based on standard performance indicators, including:
Prediction Accuracy: Mean Absolute Error (MAE), Root Mean Squared Error (RMSE).
Computational Efficiency: Execution time and resource utilization.
Scalability: Performance under varying dataset sizes and complexity.
Statistical Validation: Appropriate statistical tests, such as ANOVA or t-tests, are conducted to verify the significance of the results.
Reproducibility & Ethical Considerations
The methodology is designed to be reproducible, with detailed descriptions of datasets, algorithms, and implementation steps.
Any limitations in data selection, assumptions, or experimental conditions are clearly stated.
If real-world data is used, necessary ethical guidelines and data privacy policies are followed.
The experimental design ensures a robust evaluation of the SLPDBO-BP model, providing a solid foundation for its applicability in real-world data valuation scenarios.
The findings of this study are valid and reliable based on a well-structured experimental approach. The SLPDBO-BP model is tested on diverse datasets, ensuring that the results are consistent and generalizable.
Accuracy & Performance: The model is evaluated using standard metrics (MAE, RMSE), demonstrating improvements over existing valuation methods.
Comparative Analysis: Benchmarking against traditional models confirms that SLPDBO-BP outperforms in accuracy and efficiency.
Reproducibility: The methodology is clearly outlined, allowing other researchers to replicate the study.
Statistical Validation: The results undergo proper statistical tests to ensure significance, reducing the risk of random errors.
Overall, the study provides strong evidence that the proposed model is effective for data asset valuation.
After a detailed evaluation, we have decided to request major revisions before further consideration. While the paper proposes a novel SLPDBO-BP model for data asset valuation, significant areas require improvement. The manuscript does not adequately explain the model’s novelty and lacks a detailed discussion of why the chosen optimization strategies (Sinusoidal chaos mapping, Levy flight, adaptive weight variation) were employed and how they contribute to performance improvements. More context is needed on the practical importance of data asset value assessment and how the proposed model improves over traditional methods. The methodology section requires further details on the dataset, experimental setup, and hyperparameter tuning to ensure reproducibility. Additionally, a comparison of results with other advanced techniques is necessary, along with a clearer analysis of how improvements in error metrics (e.g., MAE, RMSE) impact practical utility. The paper also needs a stronger discussion of the findings, including performance trade-offs, limitations, and real-world applicability. Improvements to figures, captions, and overall writing clarity are also recommended. We believe that addressing these comments will significantly enhance the manuscript and look forward to reviewing your revised submission.
The manuscript entitled “SLPDBO-BP: An efficient valuation model for data asset value” has been investigated in detail. The manuscript introduces the SLPDBO-BP model for data asset value assessment, combining advanced optimization techniques like Sinusoidal chaos mapping and Levy flight with BP. While the model demonstrates improvements in error metrics, the paper lacks clarity in explaining the novelty, fails to provide sufficient experimental details, and lacks comparisons with more advanced techniques. Additionally, the manuscript needs to expand on the practical relevance of the proposed model and improve the overall writing quality for better readability. Significant revisions are required to make the paper clearer, more detailed, and more impactful.
1) The manuscript introduces the SLPDBO-BP data asset assessment model, but it fails to adequately explain what makes this model significantly different from or superior to existing methods. While the model combines Sinusoidal chaos mapping, Levy flight, and adaptive weight variation operators, the manuscript lacks a detailed explanation of why these specific strategies were chosen and how they uniquely contribute to improving the algorithm. A stronger case for the novelty and necessity of this model should be provided.
2) The paper mentions data asset value assessment as a core application but does not clearly explain how this value is defined or why it is important. The authors should provide more context on what data asset value assessment entails in a practical setting and why traditional methods fall short. It would also be helpful to explain the economic or strategic importance of accurate data asset evaluation in modern industries.
3) The optimization techniques used in the SLPDBO-BP model, such as Sinusoidal chaos mapping and Levy flight, are briefly mentioned but not well explained. Readers unfamiliar with these strategies would have difficulty understanding their purpose or how they improve the model’s performance. The manuscript should provide a more in-depth explanation of how these techniques work and include visual aids or mathematical formulations to clarify their role in the optimization process.
4) The manuscript integrates the SLPDBO algorithm with the BP (Back Propagation) algorithm for data asset value assessment but does not provide a clear rationale for this combination. Why was BP chosen as the base algorithm, and how does the SLPDBO improve its performance? The authors should elaborate on the compatibility of these two algorithms and demonstrate how SLPDBO enhances BP’s optimization capabilities.
5) The paper does not provide enough information about the experimental setup, such as the dataset used for the data asset value assessment or how the test functions for optimization were selected. The authors should specify the characteristics of the data (e.g., size, type, distribution), the computational environment (e.g., hardware specifications, software used), and the criteria for selecting the 20 test functions. These details are essential for the reproducibility and validation of the experiments.
6) The manuscript reports improvements in MAE, RMSE, and MAPE but fails to provide a thorough analysis of these results. How do the error reductions of 35.1%, 37.6%, and 38.7% impact the practical utility of the model? The authors should provide a more detailed discussion of what these error metrics represent in the context of data asset value assessment and why these reductions are significant. Additionally, a more comprehensive performance analysis, including a discussion of potential trade-offs, is needed.
7) “Discussion” section should be added in a more highlighting, argumentative way. The author should analysis the reason why the tested results is achieved.
8) The authors should clearly emphasize the contribution of the study. Please note that the up-to-date of references will contribute to the up-to-date of your manuscript. The studies named- “A robust chaos-inspired artificial intelligence model for dealing with nonlinear dynamics in wind speed forecasting; Crude oil time series prediction model based on LSTM network with chaotic Henry gas solubility optimization”- can be used to explain the methodology and chaoticity in the study or to indicate the contribution in the “Introduction” section.
9) The manuscript focuses heavily on the technical aspects of the model but lacks a discussion of real-world applications. How can the SLPDBO-BP model be used in practical data asset value assessment scenarios? The authors should provide examples or case studies demonstrating how businesses or organizations can implement this model to improve decision-making processes related to data valuation.
a) The abstract is well-structured but could include more specific details about the data asset valuation system's practical applications.
b) The manuscript uses clear language; however, some technical terms may benefit from additional explanations for a wider audience.
c) The introduction is informative but could integrate more recent references related to data asset valuation and optimization techniques.
d) Figures are visually appealing but require more descriptive captions to make them self-explanatory.
e) Keywords are relevant but could be expanded to include terms like "metaheuristics" and "data economy" for better indexing.
f) The problem statement is clear; emphasizing limitations of existing models more explicitly could enhance clarity.
g) Methodology steps of the SLPDBO algorithm are described well but would benefit from a flowchart for better visualization.
h) Details about the hyperparameter tuning process should be added to aid reproducibility.
i) The dataset preprocessing methods are briefly mentioned; providing an example would help clarify the process.
j) Justifications for using metrics like MAE, MAPE, RMSE, and MSE are solid, but including confidence intervals for results could enhance credibility.
k) The manuscript explains results showing improvements over baseline models but should address why certain algorithms underperform compared to SLPDBO.
l) While statistical significance tests like the Friedman test are included, additional explanation of the results would be beneficial.
m) The model's applicability to other datasets or domains is not discussed. Expanding on this aspect could enhance the paper's impact.
n) Scenarios where the model performs poorly should be analyzed to understand its limitations.
o) There is a lack of discussion on how businesses can adopt the proposed valuation model in real-world scenarios.
p) The integration of multiple strategies (Sinusoidal Chaos Mapping, Levy flight, and PSO) is novel and well-justified.
q) Complexity analysis is comprehensive but could be simplified for non-specialist readers.
r) Convergence plots are informative but could benefit from a legend for easier interpretation.
s) The manuscript is well-written; however, some sentences are overly long and should be split for better readability.
t) Adding a dedicated section on future work and potential extensions of the SLPDBO-BP model would enhance the manuscript.
u) The manuscript has potential but requires minor revisions to improve clarity and expand on methodological details.
v) Additional elaboration on statistical tests and real-world applicability would strengthen the paper's contributions.
w) Figures and captions need improvement for better self-explanatory content.
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.