Comparison of Different Approaches of Machine Learning Methods with Conventional Approaches on Container Throughput Forecasting

Round 1

Reviewer 1 Report

This is one interesting paper that has great potential. However, the following has to be revised before its acceptance:

1. The practical findings should be more clearly outlined in the Abstract. 

2. Research questions should be added in the Introduction section.

3. Aims of the study have to be elaborated.

4. The contributions of the paper must be enumerated in the Introduction section.

5. Literature review should be moved to a separate section; i.e., Section 2.

6. The summary of the literature has to be presented in a table format.

7. In the conclusion section there are no future research avenues. They should be provided.

8. Limitations of the paper must be explicitly outlined.

9. How general are the findings? Can they be applied to other cases?

 

Author Response

Dear reviewer,

The authors thank the reviewer for your kind comments. We have made corresponding revision according to the suggestions. Please see the following responses and revision details in the attachment.

Best Regards,

Authors

Author Response File: Author Response.pdf

Reviewer 2 Report

The article is devoted to applying nine methods to predict the historical throughput of the 20 largest container ports in the world. The study's relevance is justified by the fact that container transportation is today an essential type of international trade logistics in the world, and its changes will seriously affect the development of the international market. The COVID-19 pandemic has complicated global container logistics, so accurate forecasting of container throughput significantly contributes to stakeholders developing more accurate operational strategies and reducing costs. Therefore, the proposed study uses nine methods to predict the historical throughput of the world's 20 largest container ports and compares results within and between methods. The main takeaway from this study is that GRU is a method that can produce more accurate results with higher probability when building container throughput prediction models. The authors argue that NM can be used to quickly and efficiently evaluate container throughput when computing hardware and services are unavailable.

Despite the satisfactory quality of the article, some shortcomings need to be corrected.

1. The abstract should be expanded with numerical results obtained within the research.
2. The aim of the research should be defined.
3. State-of-the-art methods should be separated from the ones proposed by the authors.
4. The architecture of the proposed methodology should be described in more detail and grounded.
5. The data used for the experimental investigation should be described in more detail.
6. Figures 8-12 should be described in text in more detail.
7. It is recommended to include the Discussion section to compare obtained results with other research.
8. The scientific and practical novelty should be highlighted.
9. The authors' contributions should be highlighted.

In summarizing my comments, I recommend that the manuscript is accepted after major revision. 

Author Response

Dear reviewer,

The authors thank the reviewer for your kind comments. We have made corresponding revision according to the suggestions. Please see the following responses and revision details in the attachment.

Best Regards,

Authors

Author Response File: Author Response.pdf

Reviewer 3 Report

I found the paper to have some problems after thinking about it. Here are my observations:

1. The abstract section must be improved. There are gaps in the hierarchy, gap, background, why, and technique.

2-There are a few issues in the introduction part. The hierarchy, gap, purpose, and technique are all missing.

3-There are no relevant citations in the introduction. For instance, there are no references in the first two paragraphs. The authors are encouraged to cite and use these significant sources. Some suggestions include the following:

https://www.sciencedirect.com/science/article/abs/pii/S0950705119303284

https://www.sciencedirect.com/science/article/pii/S0010482522002530

https://www.mdpi.com/2227-7390/8/10/1784

https://www.sciencedirect.com/science/article/abs/pii/S0925231220316489

https://www.mdpi.com/2071-1050/13/9/5248

4-Don't leave any sections empty. Complete it using appropriate sentences. 2.1 and section 2, for instance.

5-Formulas borrowed from other works must be properly referenced.

6-A related works section is essential for such works. Section 2 with the topic of related works should be added.

Author Response

Dear reviewer,

The authors thank the reviewer for your kind comments. We have made corresponding revision according to the suggestions. Please see the following responses and revision details in the attachment.

Best Regards,

Authors

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The paper is significantly improved. 

Reviewer 2 Report

Thanks for the authors for considering the reviewer's comments and recommendations

Reviewer 3 Report

It can be accepted.