Research on Recommendation Method of Product Design Scheme Based on Multi-Way Tree and Learning-to-Rank

Round 1

Reviewer 1 Report

The paper presents a method for defining product structures according to multi-criteria optimization methods. The issue is interesting, although the AHP and TOPSIS methods are already widely used in the design phase. The paper is not natural to read. Furthermore, the method is not easily implementable by a reader. It will be useful to detail further the steps provided by the method. The structure can be improved, as the chapter of conclusions is absent. English is not fluent and sometimes affects the understanding of the concepts presented by the authors.

Therefore, the paper is deemed unsuitable to be published in the current form. The reviewer suggests the authors to improve the paper thoroughly, also taking into consideration the following comments.

• Verify that the acronyms. They are used after being defined.
• English needs careful revision by a native speaker. For many sentences, it is not possible to perceive their meaning
• The second objective of the paper, related to suppliers selection, is presented in a very superficial way that does not allow the reader to understand how it works.
• It would be useful to insert a chapter summarizing the AHP and TOPSIS methods.
• Figure 1 should be more integrated with the proposed method. For example, the activities of the flow-chart could be numbered according to the sections and steps of chapter 3.
• The authors highlight the importance of the product cost, indicating that it depends on the weight of the component. Authors could include the component cost into the list of attributes.
• In chapter 3.3.2 the authors present the RankSVM method, but it is not clear the reasons why they chose this one.
• Table S on row 281 contains the parameters "wire rope diameter" and "real diameter" while in table 6 there are "wire rope weight" and "real weight". Check if it is correct.
• Table 9 and graph 4 present the same concept. Remove one of the two.
• In table 9, what do the eight columns mean? Authors should present better how the values in this table were computed.
• The values ​​in table 10 are qualitative. Who provided these ratings?
• Add a section for conclusions

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

The authors present an interesting article on how to improve the efficiency of the product design, for this they propose an algorithm of recommendation of the product design scheme based on a classification learning system. In my opinion it is an interesting article. Just a few minor comments.

In general, authors must improve the quality of the images.

“With the continuous development of computer technology, product design patterns and methods are changing. In order to meet the increasing demand of personalized product design, it has become the development trend of new product design mode to further shorten product design cycle, reduce product cost and improve product performance.” This comment needs a reference.

“However, the current CAD software cannot effectively support the whole process of top-down product design, especially in the transition phase between conceptual design and detailed design. Most product design systems developed based on CAD software (Pro/Engineer, Soildworks) are mainly determined of a skeleton model that the main components and the overall  layout of the product by the designer.” This comment needs a reference.

In order to stay competitive in the industry, enterprises should reduce the manufacturing cost  while maintaining the product quality. Authors should support this comment with this reference. I suggest the following reference:

Cavas-Martinez, F., Garcia-Fernandez-pacheco, D.. (2019). VIRTUAL SIMULATION: A TECHNOLOGY TO BOOST INNOVATION AND COMPETITIVENESS IN INDUSTRY. DYNA, 94(2). 118-119. DOI: http://dx.doi.org/10.6036/9125

In section 2, I recommend to the authors a summary table with the referenced works, they could incorporate it as supplementary material.

The authors know the limitations of their study, they should be included in the discussion.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 3 Report

My comments and suggestions to the authors:

1. In the abstract you have written "AHP is applied...". You cannot use abbreviations in the abstract. Only in the futher text, after the abbreviations were described.
2. In the introduction is written Pro/Engineer..Isn´t it now Creo ? In the further text, you mention Creo. 
3. Introduction: there is written "AHP-TOPSIS evaluation model is...". Have you already explained what is AHP-TOPSIS ? I cannot find any description of this abbreviation.
4. Related research is done by suitable way.
5. 3rd chapter: The chapter title would be more specific.
6. Page 4: is this algorithm your ? Have you developed it ? It would be more described.
7. Page 4: what are A1, A2, ...An ? Are they matrices or only symbol or what? Try to describe it more precise.
8. Page 6: C1, C2, ...., Cm. What the index "m" means in this case ? Also a few words later is write omegai. What the parameter "i" denotes ? 
9. Equation (1): what mathematical form is it ?? In the bracket is are probably some parameters which are part of matrix but what are C1 C2 Cm along the vertical and horizontal direction ?This is not standard mathematical form. Explain it or rewrite according to basic mathematical conventions. Also I cannot find any reference to equation (1) in the paper text, which describe and deals with this equation.
10. Page 6: step 3: you write about Z but in the equation (3) is written zij. IS any relation between them ? Explain it. The same for ste 4 and variable B - equation (4) bij ...? From the text it is not clear for reader what is what.
11. Page 7: Above equation (9): "Calculate the distance Q+ and Q-". What do you mean by "distance" ? Explain it clearly.
12. Page 7: Above equation (12): you write about "RankSVM" and "NDCG". What are these terms ?? The terms are not defined, again.
13. Figure 4: graph without axes mark. Each axis has to have mark of the units in horizontal as well as vertical plane.
14. Discussion: Correct standard in prestigious journals is "Conclusion" at the end of the paper. It is also in the case, when you "use" disscussion chapter. The conclusion has to describe your own contribution.

The paper has several weaknesses. The terms are nor clearly defined, mathematical forms and parameters in equation are not clearly a properly presented. Also, it is hard to find your own contribution. Your paper presentation should have different form. You write about algorithms and methods, but from the text it is not clear what is your own contribution. How your own contribution differs from previous research in this area.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

The authors have addressed all the reviewer's comments. 

The reviewer has only minor comments.

• At row 676 there is a misuse of brackets.
• Acronyms must be presented the first time they are used in the text. For example, the AHP method is first reported on line 92, but is explained on line 174
• If possible, Figure 7.b should be translated in English
• Conclusions should be extended by including results got from the case study.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 3 Report

Thank you for your corrections. Now the paper has been improved. 

Author Response

Dear Reviewer:

Thank you for your letter and for the reviewers’ comments concerning our manuscript entitled “Research on Recommendation Method of Product Design Scheme based on Multi-way tree and Learning-to-Rank”(ID: 789465).

Special thanks to you for your good comments. 

This manuscript is a resubmission of an earlier submission. The following is a list of the peer review reports and author responses from that submission.