DETEKSI TRANSAKSI ANOMALI PADA BLOCKCHAIN DENGAN MENGGUNAKAN METODE DEEP NEURAL NETWORK (DNN)

IMAM, M. and Stiawan, Deris and Ubaya, Huda (2023) DETEKSI TRANSAKSI ANOMALI PADA BLOCKCHAIN DENGAN MENGGUNAKAN METODE DEEP NEURAL NETWORK (DNN). Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011381924124.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011381924124_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (3MB) | Request a copy
	Text RAMA_56201_09011381924124_0003047905_0216068101_01_front_ref.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (1MB)
	Text RAMA_56201_09011381924124_0003047905_0216068101_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (700kB) | Request a copy
	Text RAMA_56201_09011381924124_0003047905_0216068101_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (337kB) | Request a copy
	Text RAMA_56201_09011381924124_0003047905_0216068101_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (877kB) | Request a copy
	Text RAMA_56201_09011381924124_0003047905_0216068101_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (8kB) | Request a copy
	Text RAMA_56201_09011381924124_0003047905_0216068101_06_ref.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (234kB) | Request a copy
	Text RAMA_56201_09011381924124_0003047905_0216068101_07_lamp.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (514kB) | Request a copy

Abstract

Blockchain is a digital data bank that stores transaction data transparently. With so much interest in bitcoin, making bitcoin wallets are an attractive target for hackers. This research uses the Deep Neural Network (DNN). The dataset consists of 13 columns, 30,246,808 normal transactions and 1,326 anomalous transactions. The dataset is balanced by oversampling and undersampling techniques. The model with the best dataset ratio obtained achieved an accuracy of 84.43%. Then it was evaluated using k-fold to determine the consistency of the model in detecting and an average accuracy of 94.75% was obtained, which shows that the model has quite consistent performance.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	METODE DEEP NEURAL NETWORK (DNN)
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:	M. Imam
Date Deposited:	22 Nov 2023 01:55
Last Modified:	22 Nov 2023 01:55
URI:	http://repository.unsri.ac.id/id/eprint/130854

Actions (login required)

View Item