DETEKSI TRANSAKSI ANOMALI PADA BLOCKCHAIN DENGAN MENGGUNAKAN METODE GATED RECURRENT UNIT (GRU)

MUHAMMAD, FAISAL SOULTAN and Stiawan, Deris and Ubaya, Huda (2024) DETEKSI TRANSAKSI ANOMALI PADA BLOCKCHAIN DENGAN MENGGUNAKAN METODE GATED RECURRENT UNIT (GRU). Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011381924123.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (2MB) | Request a copy
	Text RAMA_56201_09011381924123_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (7MB) | Request a copy
	Text RAMA_56201_09011381924123_0003047905_0216068101_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_56201_09011381924123_0003047905_0216068101_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (643kB) | Request a copy
	Text RAMA_56201_09011381924123_0003047905_0216068101_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (403kB) | Request a copy
	Text RAMA_56201_09011381924123_0003047905_0216068101_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (1MB) | Request a copy
	Text RAMA_56201_09011381924123_0003047905_0216068101_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (13kB) | Request a copy
	Text RAMA_56201_09011381924123_0003047905_0216068101_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (133kB) | Request a copy
	Text RAMA_56201_09011381924123_0003047905_0216068101_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (527kB) | Request a copy

Abstract

Illegal activities such as money laundering using cryptocurrencies represented by Bitcoin have emerged. In this study, a Gated Recurrent Unit (GRU) neural network is used to identify anomalous transaction patterns in the dataset. The dataset is created by taking raw data based on yearly parameters to extract a subset of data. This subset represents data from the years 2011 to 2013 and is extracted by writing a Python code snippet. Due to the imbalance of the data, the dataset's classes are balanced using oversampling and undersampling techniques. The best model achieved an accuracy of 90.31%. Then, through k-fold validation, the model showed good consistency, with an average accuracy of 86.29%. These results indicate that the model has reliable performance in the detection task.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Anomaly Detection, Blockchain, Gated Reccurent Unit
Subjects:	Q Science > Q Science (General) > Q300-390 Cybernetics > Q325.5 Machine learning Q Science > QA Mathematics > QA75-76.95 Calculating machines > QA76.9.A25 Computer security. Systems and Data Security.
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Faisal Soultan Muhammad
Date Deposited:	06 Jun 2024 03:10
Last Modified:	06 Jun 2024 03:10
URI:	http://repository.unsri.ac.id/id/eprint/146293

Actions (login required)

View Item