Understanding Bitcoin Price Prediction Trends under Various Hyperparameter Configurations
Round 1
Reviewer 1 Report
This paper analyzes and presents the direction of hyper-parameter optimization through experiments that compose the entire combination of the timesteps, the number of LSTM units, and the ratio of the dropout layer among the most representative hyper-parameters and measure the predictive performance for each combination based on the Bitcoin price prediction model using the LSTM layer.
I have some comments regarding the manuscript:
1. In the background section, please add more literature reviews regarding the results of the previous studies that have used RNN, LSTM, and hyper-parameters.
2. Replace the "related work" section with the "results discussion" section.
3. The results could be explained in more detail.
3. Could the accuracy be measured and shown in Table 3? It is hard to understand the result if only explained as "For bitcoin price, a low ratio of dropout makes a high-accuracy prediction," whereas this study proposes the model for predicting bitcoin price. It would be better if the accuracy was also measured to see how good the model is at predicting the Bitcoin price.
4. Highlight the limitations of the proposed study in the conclusion section.
Author Response
Article Title: “Understanding Bitcoin Price Prediction Trends Under various Hyper-parameter Configurations”
To: Computers Editor
Re: Response to reviewers
Dear Editor,
Thank you for allowing a resubmission of our manuscript, with an opportunity to address the reviewers’ comments. We want to express our great appreciation to the associate editor and reviewers for their helpful comments. We were able to improve the quality of our article.
We are uploading our point-by-point response to the comments (below: response to reviewers) and an updated manuscript (Manuscript).
Best regards,
Hanul Sung et al.
Author Response File: Author Response.pdf
Reviewer 2 Report
The authors have chosen an interesting topic to work on. The research paper quality is good and authors have presented the results in detail. However, the novelty of the work is not clear. Authors need to explain how this work is novel and is different from the related works. Also, authors need to explain if their findings do apply to other crypto currencies or not?
Author Response
Article Title: “Understanding Bitcoin Price Prediction Trends Under various Hyper-parameter Configurations”
To: Computers Editor
Re: Response to reviewers
Dear Editor,
Thank you for allowing a resubmission of our manuscript, with an opportunity to address the reviewers’ comments. We want to express our great appreciation to the associate editor and reviewers for their helpful comments. We were able to improve the quality of our article.
We are uploading our point-by-point response to the comments (below: response to reviewers) and an updated manuscript (Manuscript).
Best regards,
Hanul Sung et al.
Author Response File: Author Response.pdf
Round 2
Reviewer 1 Report
All the suggestions have been addressed by the authors. Thank you