International Journal of Scientific Research in Science, Engineering and Technology
Print ISSN - 2395-1990 Available Online at : [Link]
Online ISSN : 2394-4099 doi : [Link]
Conserving Certainty of Crypto Transactions with Machine
Learning Methodologies
S. Haripriya1, Dr. D. Banumathy2, Dr. A. Jeyamurugan3, Dr. G. Madasamyraja4
1
Department of Computer Science and Engineering, Paavai Engineering College, Namakkal, India
2 Professor, Department of Computer Science and Engineering, Paavai Engineering College, Namakkal, India
3 Professor, Department of Computer Science and Engineering, Paavai Engineering College, Namakkal, India
4 Professor, Department of Information Technology, Paavai Engineering College, Namakkal, Tamilnadu, India
ARTICLEINFO ABSTRACT
Nowadays there are increase in fraudulent activities within
Article History:
cryptocurrencies transactions. To combat this, we propose a novel
Accepted: 15 May 2024 framework that integrates machine learning methodologies with the SHA-
Published: 31 May 2024 256 algorithm to enhance security and predict price fluctuations. This
Publication Issue : framework aims to provide a comprehensive solution for preventing
Volume 11, Issue 3 fraudulent activities in cryptocurrencies transactions contributing to a
May-June-2024 more secure.
Page Number : Keywords : Cryptocurrencies Transactions, Preventing Fradulent
291-293 Activities, Future Prediction.
I. INTRODUCTION Bitcoin, Ethereum, and other wide-scale
cryptocurrency coins use blockchain to process and
This paper proposes a novel framework that integrates record transactions securely. This remains the primary
machine learning methodologies, the SHA-256 use of the technology. It records the data and keeps
algorithm, and blockchain technology. The framework track of the transactions sent via the network
aims to enhance security by predicting cryptocurrency
prices and detecting fraudulent activities such as BLOCKCHAIN INTEGRATION MODULE
money laundering and somewhere payments. Through
comprehensive data processing and validation, the This module integrates blockchain technology into the
proposed system seeks to provide a secure and reliable system, enabling secure and transparent recording of
platform for cryptocurrency transactions in smart city cryptocurrency transactions. It involves setting up
environments. nodes, establishing consensus mechanisms, and
deploying smart contracts if necessary.
II. METHODOLOGY
The blockchain is secure and transparent, so each
block is irreversible and viewable by everyone.
Copyright © 2024 The Author(s): This is an open-access article distributed under the terms of the Creative 291
Commons Attribution 4.0 International License (CC BY-NC 4.0)
S. Haripriya et al Int J Sci Res Sci Eng Technol, May-June-2024, 11 (3) : 291-293
TESTING AND ANALYSIS MODULE
Once the system is setup this module conducts
comprehensive testing and analysis to evaluate its
performance. Analysis includes examining key metrics
such as precision, recall, and F1 score for fraud
detection, as well as assessing the accuracy of
cryptocurrency price predictions.
III. MODELING AND ANALYSIS
Figure 2 : Cryptocurrency future prediction
This module focuses on preparing the training data for
V. CONCLUSION
the SHA256 algorithm, which is used for
cryptographic hashing in blockchain technology. The
In conclusion, the proposed system offers a significant
training data may include a variety of inputs, such as
advancement in enhancing the security and integrity
transaction data, timestamps, and nonce values
of cryptocurrency transactions within smart city
environments. The integration of machine learning
methodologies with the SHA-256 algorithm and
blockchain technology, utilization of blockchain
technology ensures transparencyand immutability,
while machine learning techniques enhance fraud
detection capabilities.
The accurately predicting cryptocurrency prices and
Figure 1: Sha256 function
identifying fraudulent activities, the system
contributes to building a more secure and resilient
IV. RESULTS AND DISCUSSION
financial ecosystem in smart cities. The represents a
crucial step towards fostering trust and transparency in
Frontend development involves creating the visible
digital financial transactions while safeguarding their
parts of a website or application that users interact
integrity.
with, using HTML and CSS. HTML (Hypertext
Markup Language) provides the structure of the page,
ACKNOWLEDGEMENTS
defining elements like headings, paragraphs, and
images, while CSS (Cascading Style Sheets) determines
We would like to take this opportunity to say our
the presentation, including layout, colors, and fonts.
thanks to the people who have helped us make this
Backend development focuses on the server-side logic
project a reality. We wish to express our sincere thanks
of a website or application, handling tasks like database
to our honorable chairman, Shri. M.G. Bharath Kumar
interactions, user authentication, and data processing.
[Link]., M.A., M.I.S.T.E., of our Educational trust,
Python developers can build robust backend systems
Kalipatti and the Managing Directors [Link].
using frameworks like Flask, which provide tools and
Mahendiran B.E., and [Link] Ajay Prasad B.E.,
libraries to streamline development and ensure
providing an extraordinary infrastructure. We would
security and scalability.
like to express our sincere thanks to Dr.M. Senthil
Kumar M.E., Ph.D., the principal of our college, for
International Journal of Scientific Research in Science, Engineering and Technology | [Link] | Vol 11 | Issue 3 292
S. Haripriya et al Int J Sci Res Sci Eng Technol, May-June-2024, 11 (3) : 291-293
their kind encouragement and blessings to do this [5]. S. A. Alsaif, ‘‘Machine learning-based ransomware
project. We also thank Dr.U. Nilabar Nisha M.E., classification of Bitcoin transactions,’’ Appl.
MBA., Ph.D., Head of the Department, Department of Comput. Intell. Soft Comput., vol. 2023, Jan. 2023,
Computer Science and Engineering for the Art. no. 6274260, doi: 10.1155/2023/6274260.
encouragement, valuable suggestions and support in [6]. C. Ozturan, A. Sen and B. Kilic, "Transaction
doing this project. We would like to thank our internal Graph Dataset for the Ethereum Blockchain",
guide Mr.A. Mohanasudaram M.E., Department of Zenodo, pp. 4718440, Apr. 2021.
Computer Science and Engineering for the kind co- [7]. Time-series Bitcoin price predictions with high-
operative and support rendered in making our project dimensional features using machine
as success. We would like to say our sincere thanks to learningMohammedMudassir1 Devrim Unal1
all other faculties, Department of Computer Science Shada Bennbaia 20 June Mohammad
and Engineering for their active and kind guidance and Hammoudeha division of Springer Nature 2020 is
advices for our project. Above all we would like to Springer-Verlag London Ltd.
express my sincere gratitude and thanks to our parents [8]. H. Sebastião and P. Godinho, “Forecasting and
for their valuable comments and suggestions for trading cryptocurrencies with machine learning
making this success. under changing market conditions,” Financ.
Innov., vol. 7, no. 1, pp. 1–30, 2021.
III. REFERENCES [9]. Elbaghdadi A, Mezroui S, El Oualkadi A (2021) K-
Nearest Neighbors Algorithm (KNN): An
[1]. M. Ul Hassan, M. H. Rehmani, and J. Chen, Approach to Detect Illicit Transaction in the
‘‘Anomaly detection in blockchain networks: A Bitcoin Network. In: Integration Challenges for
comprehensive survey,’’ IEEE Commun. Surveys Analytics, Business Intelligence, and Data Mining:
Tuts., vol. 25, no. 1, pp. 289–318, 1st Quart., 2023, IGI Global, 2021, pp 161–178.
doi: 10.1109/COMST.2022.3205643. [10]. Chen B, Fushan W, Chunxiang G (2021) Bitcoin
[2]. P. Raghavan and N. E. Gayar, "Fraud Detection Theft Detection Based on Supervised Machine
using Machine Learning and Deep Learning", Learning Algorithms. Security and
2019 International Conference on Computational Communication Networks 2021.
Intelligence and Knowledge Economy (ICCIKE),
pp. 334-339, 2020, [online] Available:
[Link]
31.
[3]. Varmedja, D., Karanovic, M., Sladojevic, S.,
Arsenovic, M. and Anderla, A., 2019, March.
Credit card fraud detection-machine learning
methods. In 2019 18th International Symposium
INFOTEH-JAHORINA (INFOTEH) (pp. 1-5).
IEEE.
[4]. B. Kiliç, A. Sen, and C. Özturan, ‘‘Fraud detection
in blockchains using machine learning,’’ in Proc.
4th Int. Conf. Blockchain Comput. Appl. (BCCA),
Sep. 2022, pp. 214–218, doi: 10.1109/BCCA55292.
2022.9922045.
International Journal of Scientific Research in Science, Engineering and Technology | [Link] | Vol 11 | Issue 3 293
