ANALISA TRANSAKSI PADA BLOCKCHAIN DENGAN METODE MACHINE LEARNING

VADITHYA, MUHAMMAD DIMAS and Ubaya, Huda (2025) ANALISA TRANSAKSI PADA BLOCKCHAIN DENGAN METODE MACHINE LEARNING. Undergraduate thesis, Sriwijaya University.

	Text RAMA_56201_09011382126137.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_56201_09011382126137_TURNITIN.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (4MB) | Request a copy
	Text RAMA_56201_09011382126137_0216068101_01__FRONT_REF.pdf - Accepted Version Available under License Creative Commons Public Domain Dedication. Download (3MB)
	Text RAMA_56201_09011382126137_0216068101_02.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (216kB) | Request a copy
	Text RAMA_56201_09011382126137_0216068101_03.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (385kB) | Request a copy
	Text RAMA_56201_09011382126137_0216068101_05.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (127kB) | Request a copy
	Text RAMA_56201_09011382126137_0216068101_04.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (793kB) | Request a copy
	Text RAMA_56201_09011382126137_0216068101_06_REF.pdf - Bibliography Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (106kB) | Request a copy
	Text RAMA_56201_09011382126137_0216068101_07_LAMP.pdf - Accepted Version Restricted to Repository staff only Available under License Creative Commons Public Domain Dedication. Download (868kB) | Request a copy

Abstract

Blockchain offers high security; however, the performance of transactions on this network remains a subject that requires further analysis. Transaction success in blockchain is influenced by various factors.This study aims to analyze transaction performance on the blockchain using the K-Means Clustering method. The analysis focuses on the parameters of Gas Limit and Gas Consumed to understand the factors contributing to transaction success and failure. The methods used include data preprocessing, determining the number of clusters, implementing the K-Means algorithm, and evaluating performance using the Silhouette Score. Data visualization through scatter plots and boxplots helps identify patterns of imbalance in gas allocation. The results of the study show that the K-Means method successfully grouped transaction data into two clusters: the first cluster represents transactions with a low Gas Limit that have a higher potential for failure, while the second cluster consists of transactions with a higher Gas Limit and greater chances of success. The evaluation using the Silhouette Score yielded an average value of 0.98, indicating excellent clustering performance with optimal separation between clusters. This study provides a clear overview of blockchain transaction performance and identifies the causes of transaction failures as an initial step toward improving system efficiency.

Item Type:	Thesis (Undergraduate)
Uncontrolled Keywords:	Blockchain, IOTA, Transaction, Performance Evaluation
Subjects:	Q Science > Q Science (General) > Q334-342 Computer science. Artificial intelligence. Algorithms. Robotics. Automation. T Technology > T Technology (General) > T57-57.97 Applied mathematics. Quantitative methods T Technology > T Technology (General) > T57-57.97 Applied mathematics. Quantitative methods > T57.5 Data processing Cf. HF5548.125+ Business data processing Operations research. Systems analysis
Divisions:	09-Faculty of Computer Science > 56201-Computer Systems (S1)
Depositing User:	Unnamed user with email 09011382126137@student.unsri.ac.id
Date Deposited:	23 Jan 2025 03:51
Last Modified:	23 Jan 2025 03:51
URI:	http://repository.unsri.ac.id/id/eprint/166055

Actions (login required)

View Item