A Hybrid Machine Learning Model for Predicting USA NBA All-Stars

Round 1

Reviewer 1 Report

Overall Comments:

 This paper presents a prediction system for NBA All-Stars by using publicly available statistics and open-source methods. This paper defined a standard metrics to measure the accuracy of the model and selects the best performing three (The random forest classifier, the AdaBoost classifier, and the MLP classifier) from the six existing models to propose a hybrid proposal. The hybrid proposal used in this paper has greatly improved the accuracy of prediction.

In general, the topic in this paper is interesting. However, there are some problems in the logic of writing, the authors put the main innovation of research in the last place, and in the first half of a large number of other people's research results, it is difficult to understand the research ideas. Thus, the paper in present form is not ready for publication. The following comments and feedback could hopefully assist the authors in future revisions.

Specific Comments:

1. Introduction: In this part, the authors mentioned a large number of evolution history about NBA and the prediction methods used in various athletics from ancient times to the present. However, it lacks a clear explanation of the paper’s research methods and ideas.
2. Methods:
   1. The authors proposed a standard metric to measure the accuracy of the six existing models but lacks an explanation of the effectiveness of this metric. Why are four variables proposed, but only two of them are used to form the metric?
   2. Based on the three existing models that perform best on the metric proposed by themselves, the paper published a hybrid model as the innovation point, is it reliable?

Author Response

Reply to the reviewer attached

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments from Reviewers:

 

1. The abstract is too general, especially at the end where the main results are summarized (please include some numerical valus also)

 

2. The authors have improved the manuscript, but the description of the methodology is still hard to read.

 

3. The problem definition of this work is not clear. The drawbacks of each. Conventional technique should be described clearly. You should emphasize the difference with other methods to clarify the position of this work further.

 

4. Explain novelty this topic research?

 

5. The details of the proposed system Artificial Neural Network (Artificial Intellegence) method/model (ANN, such as number of neurons, pattern recognition, layer, etc., are not clear.

 

6. Compare the proposed analysis and model with other researches analysis model. In this manuscript papar, the comparison was performed between historical and simulated only. There are many previous works. You should emphasize the difference with other researches’ analysis model. And add more comparison data.

 

7. Symbols, must be explained, and the function and significance of these equations discussed

Comments for author File: Comments.pdf

Author Response

Reply to the reviewer attached

Author Response File: Author Response.pdf

Reviewer 3 Report

Dear Authors.

This paper (A hybrid Machine Learning model for predicting NBA All-Stars) provides little information. But, it is very good motivation and result. So, I give Major Revision.

The strength of the paper included: the topic is good and interesting.

#1. Code and Simulation
What kind of Simulation/Coding language did you use?
-Please add/more version and description.

-Simulation/Coding language environment.

#2. Methods.
-They should be described with sufficient detail to allow others to replicate and build on published results. New methods and hybrid Machine Learning should be described in detail while well-established methods can be briefly described and appropriately cited. Give the name and version of any software used and make clear whether computer code used is available. Include any pre-registration codes (Methods).

#3.
Does the introduction provide sufficient background and include all relevant references? Must be improved
Is the research design appropriate? Can be improved
Are the methods adequately described? Can be improved
Are the results clearly presented? Can be improved
Are the conclusions supported by the results? Must be improved

#4. Contribution
-It is almost impossible to understand the contribution of the paper.

#5. Completeness and Related Work (In Introduction and Related Work) are poor.

Also, improve more related works, more to 15 new papers published from 2018~2021 by major publishers such as IEEE, ACM, Springer, Elsevier, MDPI, and Wiley. (Need new papers)

#6. English language: Good
English language and style is/need "minor" spell check required.

#7.
-What is Supporting the Pre-hospital Healthcare Process ? (Study more)

#8.
Scientific Soundness: Low

#9. Conclusion Need:
-Future work" write more. (Must be improved)
-This section is not mandatory, but can be added to the manuscript if the discussion is unusually long or complex.
-Conclusions supported by the results. (Write more)

#10. Check Title
(In system) A hybrid Machine Learning model for predicting NBA All-Stars 
->A hybrid Machine Learning model for predicting USA NBA All-Stars

(In paper) A prediction system for NBA All-Stars
->A Prediction System for USA NBA All-Starsars 

Author Response

Reply to the reviewer attached

Author Response File: Author Response.pdf

Round 2

Reviewer 3 Report

Dear Authors.
The revision adequately address the concerns expressed in last review. So, I recommend that this revised manuscript can now be recommended for publication (Accept as is).

Author Response

Thank you very much for your kind comments. We are glad and grateful you recommended our manuscript for publication

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.