Analysis of Circular Price Prediction Strategy for Used Electric Vehicles

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This paper addresses the need for a reliable price prediction system for used electric EVs in China, due to the recent price wars and declining prices in the market. The topic is interesting.

1.        The introduction provides a good overview of the market dynamics and the need for accurate price predictions. However, it would be beneficial to include more background on the specific challenges faced by the Chinese EV market and include more literature on vehicle price prediction.

2.        The implications drawn from Figure 2 are not fully explained. It would be beneficial for the authors to elaborate on these features. For instance, the specific definition of "suggested price" should be clarified—is it the price for a new vehicle? The new vehicle price could significantly impact the used vehicle price.

3.        How this study handles the training and testing data, especially for the three rounds of model training, needs further explanation. The authors should clarify how they ensure there is no data leakage from the training sets to the test sets.

4.        Including plots that compare the real versus predicted values in the results section would enhance the paper. Visual comparisons can provide clearer insights into the model's accuracy and performance.

5.        The discussion on how government policies and incentives influence EV prices is a strong point, but it could be expanded to include a more detailed analysis of potential policy changes and their anticipated effects on the market.

Comments on the Quality of English Language

The quality of English in the paper is generally good but could benefit from some improvements in clarity, consistency, and precision.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 2 Report

Comments and Suggestions for Authors

The paper focuses on the prediction of used electric vehicle (EV) prices in China, comparing various methods such as random forest and gradient boosting regression tree. Utilizing web scraping techniques, a large dataset of EV information is collected and processed. The study proposes a circular pricing concept to update prices based on real-time data.

 

Strengths:

1.       The paper addresses an important issue of predicting used electric vehicle (EV) prices in China, which is relevant and timely given the increasing popularity of EVs.

2.       2The study compares several methods for predicting used EV prices, including random forest and gradient boosting regression tree, providing a comprehensive analysis.

3.       The use of web scraping techniques to gather a large amount of data on EVs from the Autohome website demonstrates a thorough data collection process.

4.       The incorporation of evaluation criteria such as mean square error, root mean square error, mean absolute error, and R-squared provides a robust assessment of the prediction models.

 

Areas for Improvement:

1.       The paper could benefit from a more detailed explanation of the methodology used for data processing and model training to enhance the reproducibility of the study.

2.       The discussion on the factors influencing used EV pricing could be expanded to provide a deeper understanding of the market dynamics.

3.       The limitations of the study, such as the potential biases in data collection or model assumptions, should be clearly stated to ensure transparency.

4.       The paper lacks a comparison with existing literature on used car price prediction, which could provide additional context for the study.

5.       Also, the literature review may be improved by citing more relevant papers. Just list several as follows.

Circular economy strategies for electric vehicle batteries reduce reliance on raw materials

Technical and economic analysis of battery electric buses with different charging rates

 

Specific Suggestions:

1.       Provide more insights into the implications of the findings for both buyers and sellers of used EVs in China.

2.       Consider conducting sensitivity analyses to test the robustness of the prediction models under different scenarios.

3.       Include a section on future research directions to guide further studies in this area.

4.       Clarify the practical implications of the proposed circular pricing method and its potential impact on the used car market.

 

Conclusion:

Overall, the paper presents a valuable contribution to the field of used EV price prediction in China. By comparing different prediction methods and proposing a novel pricing strategy, the study offers insights that can benefit both stakeholders in the EV market. However, to enhance the quality of the paper, it is recommended to address the areas for improvement and incorporate specific suggestions for further refinement.

Comments on the Quality of English Language

Good

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Reviewer 3 Report

Comments and Suggestions for Authors

1.     There are formatting issues in the manuscript

2.     XG boost is a library that allows the implementation of machine learning, not a machine learning method itself. It should not be at the same level as machine learning methods (line 45).

3.     Narrative logic is broken. A comparison table of methods is given after the proposed technique.

4.     Why does KNN is better than other algorithms for the solving problem ? An explanation of the comparison for KNN should be given.

5.  Is crawling time a constant value or does it happen by trigger (which trigger/event)?

6.     Not found references for related work. How do other researchers solve that problem? Any work? Why is the proposed work unique and better than other work in the sphere? Provide more background and related work.

 

7.     Limitations of proposed method are not specified.

Author Response

Please see the attachment

Author Response File: Author Response.pdf

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

The authors addressed all the comments.

Reviewer 2 Report

Comments and Suggestions for Authors

The authors have dealt with all my concerns.

Reviewer 3 Report

Comments and Suggestions for Authors

Thank you for your answers.

Answers are clear. All comments were updated in the new version.