Used Car Price Prediction Based on the Iterative Framework of XGBoost+LightGBM

Round 1

Reviewer 1 Report

XGBoost is a decision-tree-based ensemble Machine Learning algorithm that uses a gradient boosting framework. In prediction problems involving unstructured data (images, text, etc.) artificial neural networks tend to outperform all other algorithms or frameworks.

Advantages:

This is a good analytical report with practical experiments implementation. The mathematical part is acceptable.

Main moto of manuscript: “... experimental results show ... has a better prediction accuracy than the random forest and deep network…”

The design of manuscript is quality and well structured.

Disadvantages:

Some remarks and questions :

-        -   Line 310: wrong table number and caption

-        -   some references in the bibliography have only one author, but you useet al. For example, [17] (Line 371)

-          - please give XGBoost and LightGBM transcript at first citation (in the abstract part)

-          - you says (line 219) that DXL includes XGBoost and LightGBM. shouldn't you have put DXL in the title of the article?

-          - you use this method for used cars price prediction. what will change significantly for the new cars prediction?

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Reviewer 2 Report

This paper deals with an exciting topic. The article has been read carefully, and some minor issues have been highlighted in order to be considered by the author(s).

#1 What is the motivation of this paper?

#2 What is the contribution and novelty of this paper?

#3 What is the advantage of this paper?

#4 Which evaluation metrics did you used for comparison?

#5 It would be good if security domains (adversarial example) for the deep neural network would be reflected in the related work such as Advanced ensemble adversarial example on unknown deep neural network classifiers, Detecting backdoor attacks via class difference in deep neural networks, Robust CAPTCHA image generation enhanced with adversarial example methods.

#6 Since the text size of Figure 7 is larger than the text size of the text, it is necessary to reduce the size of Figure 7 a bit.

#7 The structure and hyperparameters of the used model are expressed in tabular form.

#8 In Figure 2 and Figure 3, it looks like we need a black and green legend on the graph.

Author Response

Please see the attachment.

Author Response File: Author Response.pdf

Round 2

Reviewer 2 Report

I recommend the acceptance.

Author Response

I am glad that you approve of this manuscript and thank you very much for accepting the proposal.