Candlestick Pattern Recognition in Cryptocurrency Price Time-Series Data Using Rule-Based Data Analysis Methods

Round 1

Reviewer 1 Report

Comments and Suggestions for Authors

This report presents rule-based methods for identifying candlestick patterns in cryptocurrency trading data. While the report presents several findings, such as the identification of three types of patterns using predefined rules, it also underscores significant concerns and potential challenges that necessitate further investigation.

1. Numerous studies and published code sets analyze candlestick patterns in both stock market and cryptocurrency trading. Many of these studies utilize combinations of rules or conditions to recognize these patterns. The authors should provide a comprehensive review of these existing studies and tools, highlighting the differences between their work and previous research. While the authors assert that this study introduces novel and impactful methods for rule-based candlestick pattern recognition, the current text does not sufficiently support this assertion.

2. The authors have conducted data analysis in this study; however, critical information regarding data collection and data cleaning is absent. Without these details, it is impossible to evaluate the validity of the current analysis.

3. This report has identified patterns defined by rules within historical data. However, there is a paucity of statistical results demonstrating the effectiveness of the methods employed. While the authors report precision, recall, and F1 scores, the methodology used to calculate these results remains undisclosed. If the detected patterns are to be compared to the "ground truth," the authors should initially provide details regarding the model target, including the method used to derive them and statistical analyses validating their definition.

The authors compare the results to manual identification; however, there is no information regarding how the manual process was conducted and validated. Without this critical information, it is not appropriate to use manual identification as a basis for comparison to demonstrate the advantages of the proposed method.

The methods have been tested using four years of data; however, the Ethereum market has a trading history spanning eight to nine years. The authors should conduct more comprehensive testing using all available data. Moreover, as the authors assert the effectiveness of the proposed methods in cryptocurrency trading, it is necessary to evaluate the generalizability of these methods by testing them on trading data from various types of cryptocurrencies.

Comments on the Quality of English Language

This report needs minor revision to enhance the language.

Author Response

Dear Anonymous Reviewer,

Thank you for your thoughtful and constructive feedback on our manuscript. We greatly appreciate the time and effort you have invested in providing insightful comments that have significantly helped us to enhance the quality and clarity of our paper. In this revised version we have carefully addressed all the comments and suggestions raised. In file attached, we provide detailed explanations of how we have addressed each comment. All revisions have been marked in color within the manuscript for ease of reference.

Thank you for your consideration.

Sincerely, Authors

Author Response File: Author Response.docx

Reviewer 2 Report

Comments and Suggestions for Authors

Comments for author File: Comments.pdf

Author Response

Dear Anonymous Reviewer,

Thank you for your thoughtful and constructive feedback on our manuscript. We greatly appreciate the time and effort you have invested in providing insightful comments that have significantly helped us to enhance the quality and clarity of our paper. In this revised version we have carefully addressed all the comments and suggestions raised. In file attached, we provide detailed explanations of how we have addressed each comment. All revisions have been marked in color within the manuscript for ease of reference.

Thank you for your consideration.

Sincerely, Authors

Author Response File: Author Response.docx

Reviewer 3 Report

Comments and Suggestions for Authors

Candlestick Patterns Recognition in Cryptocurrency Prices Time-Series Data using Rule-Based Data Analysis Methods introduces an innovative rule based data analysis methodology for the recognition of candlestick patterns within the cryptocurrency market, leveraging the power of Python for intellectual data analysis. After reading the paper, I think that the study meets the requirement to be published in the journal with very minor revision. Just as a minor comment, it could be interesting to underline future research lines that could consider the application of the methodology in other (smaller) cryptocurrencies and relevant sectors in the recent years such as

Fan tokens: Vidal-Tomás, D. (2024). Blockchain, sport and fan tokens. Journal of Economic Studies, 51(1), 24-38.

Gaming: Dowling, M. (2022). Fertile LAND: Pricing non-fungible tokens. Finance Research Letters, 44, 102096.

Metaverse: Vidal-Tomás, D. (2023). The illusion of the metaverse and meta-economy. International Review of Financial Analysis, 86, 102560.

Decentralised finance: Ugolini, A., Reboredo, J. C., & Mensi, W. (2023). Connectedness between DeFi, cryptocurrency, stock, and safe-haven assets. Finance Research Letters, 53, 103692.

Among other sectors

Author Response

Dear Anonymous Reviewer,

Thank you for your thoughtful and constructive feedback on our manuscript. We greatly appreciate the time and effort you have invested in providing insightful comments that have significantly helped us to enhance the quality and clarity of our paper. In this revised version we have carefully addressed all the comments and suggestions raised. In file attached, we provide detailed explanations of how we have addressed each comment. All revisions have been marked in color within the manuscript for ease of reference.

Thank you for your consideration.

Sincerely, Authors

Author Response File: Author Response.docx

Round 2

Reviewer 1 Report

Comments and Suggestions for Authors

I appreciate the authors' responses and revisions. The inclusion of additional information enhances the integrity and transparency of this paper. Most of my concerns and suggestions have been addressed in this version. However, I do have a follow-up comment. More details should be provided regarding data cleaning. For instance, the IQR method has been used to identify outliers. This method is inherently disadvantaged when the distribution of data is skewed and may misidentify outliers that are actually true signals. The authors should provide more evidence on how much data has been excluded and justify their approach in effectively removing noise while minimizing misclassification. Such efforts would greatly enhance the validity of data collection and preparation in this report. If the authors decide to make edits based on this feedback, I do not need to review the revised version again.

Comments on the Quality of English Language

Minor revision of the language is suggested.

Author Response

Comments 1:
More details should be provided regarding data cleaning. For instance, the IQR method has been used to identify outliers. This method is inherently disadvantaged when the distribution of data is skewed and may misidentify outliers that are actually true signals. The authors should provide more evidence on how much data has been excluded and justify their approach in effectively removing noise while minimizing misclassification. Such efforts would greatly enhance the validity of data collection and preparation in this report.

Response 1:

Dear Reviewer,

Thank you for your valuable feedback. In response to your suggestion, we have provided additional details on our data cleaning process, specifically regarding the use of the IQR method for outlier detection. We included information on the percentage of data excluded and justified our approach to effectively remove noise while minimizing misclassification.

We have highlighted these changes in the new version of the manuscript for your convenience.

Sincerely,
Authors

Reviewer 2 Report

Comments and Suggestions for Authors

I thank the authors for addressing my main concerns. There is no additional recommendations.

 

Author Response

Dear Reviewer,

We would like to extend our sincere gratitude for your positive feedback and for recognizing the efforts we put into addressing your main concerns. We are pleased that our revisions have met your expectations and that you have no additional recommendations.

Your constructive input has been invaluable in enhancing the quality and presentation of our paper. We are confident that the improvements made have significantly strengthened our manuscript.

Thank you once again for your time and thoughtful review.

Sincerely,
The Authors