Melola Discovery

← Melola Discovery

Journal SINTA 1

Optimizing K-Means Clustering Parameters for Mapping Smart Contract Transaction Characteristics: A Comparative Analysis of Evaluation Metrics in the IOTA Ecosystem

Indonesian Journal of Electical Engineering and Informatics (IJEEI) · Vol. 14 No. 1 (2026) · pp. 306–324

DOI
10.52549/ijeei.v14i1.7741
ISSN
2089-3272, 2089-3272
Published
2026-03-31
Publisher
IAES Indonesian Section
Language
en

Abstract

Smart contracts are already a major development in digital transaction automation thanks to blockchain technology, but their operational efficiency is still greatly impacted by resource consumption, transaction success rates, and gas cost dynamics. This study aims to optimize the K-Means Clustering algorithm's parameters in order to map the characteristics of smart contract transactions in the IOTA ecosystem and provide thorough insights into the efficiency of gas allocation. Using a massive dataset of 566,303 empirical transactions from the IOTA Tangle, three key metrics the Silhouette Coefficient, Davies-Bouldin Index, and Calinski-Harabasz Index were compared to verify the quality of the clustering. With a Silhouette Coefficient value of 0.9851, Davies-Bouldin Index of 0.4622, and Calinski-Harabasz Index of 741,423.92, quantitative evaluation results demonstrate that the 3- cluster structure performs better than two clusters. These results validate the 3-cluster model's ability to more accurately divide transactions into categories that are efficient, complex, and gas-inefficient. The results of this mapping can serve as the foundation for creating an automated recommendation system for optimizing transaction costs in decentralized networks. This study shows that the Gas Limit and Gas Consumed indicators are crucial predictors of transaction efficiency.

Keywords

Collaboration network of the authors

40 authors · 132 co-authorship links · 29 across different organisations · showing the 40 most connected

Hover or tap a name to highlight its co-authors. Double-click to open the author's page.

  • Sriwijaya University
  • Universitas Dinamika Bangsa
  • Sultan Agung Islamic University
  • Udayana University
  • Universitas Ahmad Dahlan
  • Al Baha University
  • Diponegoro University
  • Other organisations
  • Affiliation unknown
  • Different organisations
  • Same organisation
  • Affiliation unknown
  • Thicker line = more joint articles · bigger circle = more articles
Show as table
Co-authorOrganisationJoint articles
Rahmat BudiartoAl Baha University14
Mohd. Yazid IdrisAffiliation unknown6
Sharipuddin SharipuddinUniversitas Dinamika Bangsa5
Benni PurnamaAffiliation unknown5
Kurniabudi KurniabudiUniversitas Dinamika Bangsa4
Darmawijoyo HanapiAffiliation unknown4
Siti NurmainiSriwijaya University4
Ahmad ZarkasiAffiliation unknown4
Tole SutiknoUniversitas Ahmad Dahlan3
Zainuddin NawawiSriwijaya University3
Munawar Agus RiyadiDiponegoro University2
Lina HandayaniUniversitas Ahmad Dahlan2
Imam Much Ibnu SubrotoSultan Agung Islamic University2
Sri Arttini Dwi PrasetyowatiSultan Agung Islamic University2
Suci DwijayantiSriwijaya University2
Eko Arip WinantoUniversitas Dinamika Bangsa2
Ahmad HeryantoAffiliation unknown2
Mohd Yazid Bin IdrisAffiliation unknown2
Darmawijoyo DarmawijoyoAffiliation unknown2
Bedine KerimAffiliation unknown2
Muhammad Khosyi'inAffiliation unknown2
Hadipurnawan SatriaSriwijaya University2
Anggina PrimanitaSriwijaya University2
I Gede YusaUdayana University1
Dewi BungaAffiliation unknown1
Ni Ketut Supasti DharmawanUdayana University1
Desak Putu Dewi KasihUdayana University1
Eka Nuryanto BudisusilaSultan Agung Islamic University1
Yaya Sudarya TrianaMercu Buana University1
Mohd Azam OsmanUniversiti Sains Malaysia1
Silfani Sandra MirandaSriwijaya University1
Dlulil AmriSriwijaya University1
Robi PrasetioSriwijaya University1
Woro Ayu PrasetyaningtyasAffiliation unknown1

Affiliations come from OpenAlex; journal OAI-PMH metadata carries none. Authors without an OpenAlex ID are matched by name, which can merge or split people.

Metadata source: OAI-PMH (metadata jurnal) http://section.iaesonline.com/index.php/IJEEI/oai, first harvested 8 Nov 2026, last seen 8 Nov 2026.
Original metadata (oai_dc) 
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en">Optimizing K-Means Clustering Parameters for Mapping Smart Contract Transaction Characteristics: A Comparative Analysis of Evaluation Metrics in the IOTA Ecosystem</dc:title>
	<dc:creator xml:lang="en">Ubaya, Huda</dc:creator>
	<dc:creator xml:lang="en">Stiawan, Deris</dc:creator>
	<dc:creator xml:lang="en">Suprapto, Bhakti Yudho</dc:creator>
	<dc:creator xml:lang="en">Ekaputra, Rivaldi Febrian</dc:creator>
	<dc:creator xml:lang="en">Afifah, Nurul</dc:creator>
	<dc:creator xml:lang="en">Ningrum, Septiani Kusuma</dc:creator>
	<dc:subject xml:lang="en">IOTA Tangle</dc:subject>
	<dc:subject xml:lang="en">Smart Contract</dc:subject>
	<dc:subject xml:lang="en">K-Means Clustering</dc:subject>
	<dc:subject xml:lang="en">Silhouette Coefficient</dc:subject>
	<dc:subject xml:lang="en">Davies-Bouldin Index</dc:subject>
	<dc:subject xml:lang="en">Calinski-Harabasz Index</dc:subject>
	<dc:description xml:lang="en">Smart contracts are already a major development in digital transaction automation thanks to blockchain technology, but their operational efficiency is still greatly impacted by resource consumption, transaction success rates, and gas cost dynamics. This study aims to optimize the K-Means Clustering algorithm's parameters in order to map the characteristics of smart contract transactions in the IOTA ecosystem and provide thorough insights into the efficiency of gas allocation. Using a massive dataset of 566,303 empirical transactions from the IOTA Tangle, three key metrics the Silhouette Coefficient, Davies-Bouldin Index, and Calinski-Harabasz Index were compared to verify the quality of the clustering. With a Silhouette Coefficient value of 0.9851, Davies-Bouldin Index of 0.4622, and Calinski-Harabasz Index of 741,423.92, quantitative evaluation results demonstrate that the 3- cluster structure performs better than two clusters. These results validate the 3-cluster model's ability to more accurately divide transactions into categories that are efficient, complex, and gas-inefficient. The results of this mapping can serve as the foundation for creating an automated recommendation system for optimizing transaction costs in decentralized networks. This study shows that the Gas Limit and Gas Consumed indicators are crucial predictors of transaction efficiency.</dc:description>
	<dc:publisher xml:lang="en">IAES Indonesian Section</dc:publisher>
	<dc:date>2026-03-31</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://section.iaesonline.com/index.php/IJEEI/article/view/7741</dc:identifier>
	<dc:identifier>10.52549/ijeei.v14i1.7741</dc:identifier>
	<dc:source xml:lang="en">Indonesian Journal of Electrical Engineering and Informatics (IJEEI); Vol. 14 No. 1: March 2026; 306-324</dc:source>
	<dc:source>2089-3272</dc:source>
	<dc:source>2089-3272</dc:source>
	<dc:language>en</dc:language>
	<dc:relation>https://section.iaesonline.com/index.php/IJEEI/article/view/7741/1073</dc:relation>
</oai_dc:dc>