<?xml version="1.0" encoding="UTF-8"?>
<!DOCTYPE ArticleSet PUBLIC "-//NLM//DTD PubMed 2.7//EN" "https://dtd.nlm.nih.gov/ncbi/pubmed/in/PubMed.dtd">
<ArticleSet>
<Article>
<Journal>
				<PublisherName>مٰؤسسه آموزش عالی فردوس</PublisherName>
				<JournalTitle>اکتشاف و پردازش هوشمند دانش</JournalTitle>
				<Issn>2783-3607</Issn>
				<Volume>5</Volume>
				<Issue>17</Issue>
				<PubDate PubStatus="epublish">
					<Year>2025</Year>
					<Month>08</Month>
					<Day>23</Day>
				</PubDate>
			</Journal>
<ArticleTitle>Clustering Iranian Banks&#039; Business Models via Financial Indicators</ArticleTitle>
<VernacularTitle>Clustering Iranian Banks&#039; Business Models via Financial Indicators</VernacularTitle>
			<FirstPage></FirstPage>
			<LastPage></LastPage>
			<ELocationID EIdType="pii">242042</ELocationID>
			
<ELocationID EIdType="doi">10.30508/kdip.2026.552896.1166</ELocationID>
			
			<Language>FA</Language>
<AuthorList>
<Author>
					<FirstName>مهران</FirstName>
					<LastName>ریکی</LastName>
<Affiliation>گروه مهندسی کامپیوتر،دانشگاه ملی مهارت(فنی و حرف های )،تهران،ایران</Affiliation>
<Identifier Source="ORCID">0000-0003-4941-2084</Identifier>

</Author>
<Author>
					<FirstName>فاطمه</FirstName>
					<LastName>محمدی</LastName>
<Affiliation>دانشجوی کارشناسی ارشد علوم کامپیوتر، دانشکده ریاضی، آمار و علوم کامپیوتر، دانشگاه سیستان و بلوچستان، زاهدان، ایران</Affiliation>

</Author>
<Author>
					<FirstName>پوریا</FirstName>
					<LastName>خازنی</LastName>
<Affiliation>دانشجوی کارشناسی ارشد مدیریت فناوری اطلاعات، دانشکده مدیریت و اقتصاد، دانشگاه سیستان و بلوچستان، زاهدان، ایران</Affiliation>

</Author>
</AuthorList>
				<PublicationType>Journal Article</PublicationType>
			<History>
				<PubDate PubStatus="received">
					<Year>2025</Year>
					<Month>10</Month>
					<Day>12</Day>
				</PubDate>
			</History>
		    <Abstract>The Iranian banking sector evolved significantly from 2018 to 2022, shifting from traditional deposit-based models to digital and innovative ones amid economic sanctions and technological progress. This study classifies the business models of 15 major Iranian banks using k-means cluster analysis on multidimensional financial indicators and qualitative strategy assessments.Quantitative metrics include non-interest income to total income ratio (diversification), loan-to-deposit ratio (lending intensity), return on assets (ROA; profitability), investment-to-assets ratio (asset strategy), and non-performing loans (NPL) ratio (risk exposure). Qualitative factors evaluate digital adoption, niche focus, and innovation.Optimal clusters were identified as k=3 via Elbow (inflection at k=3), Silhouette (peak at k=4, but k=3 selected for balance), and Gap methods, with ANOVA and Tukey tests confirming significant inter-group differences (p&lt;0.05).Results reveal three archetypes: Traditional commercial banks (mostly state-owned; ROA≈1.4%; interest-dominant, high NPLs, low diversification); Specialized banks (niche-oriented, e.g., agriculture; ROA≈1.7%; balanced portfolios); Innovative banks (private-led; ROA≈2.2%; high non-interest income, digitalization, lower NPLs).Findings partially align with state-private ownership divides but highlight private sector innovation trends. Implications: Tailored regulations to promote diversification in traditional models and enhance cyber resilience for innovative ones. Policymakers should foster tech partnerships. Future research could incorporate macroeconomic factors like inflation for longitudinal insights, aiding sustainable banking development in Iran.</Abstract>
			<OtherAbstract Language="FA">The Iranian banking sector evolved significantly from 2018 to 2022, shifting from traditional deposit-based models to digital and innovative ones amid economic sanctions and technological progress. This study classifies the business models of 15 major Iranian banks using k-means cluster analysis on multidimensional financial indicators and qualitative strategy assessments.Quantitative metrics include non-interest income to total income ratio (diversification), loan-to-deposit ratio (lending intensity), return on assets (ROA; profitability), investment-to-assets ratio (asset strategy), and non-performing loans (NPL) ratio (risk exposure). Qualitative factors evaluate digital adoption, niche focus, and innovation.Optimal clusters were identified as k=3 via Elbow (inflection at k=3), Silhouette (peak at k=4, but k=3 selected for balance), and Gap methods, with ANOVA and Tukey tests confirming significant inter-group differences (p&lt;0.05).Results reveal three archetypes: Traditional commercial banks (mostly state-owned; ROA≈1.4%; interest-dominant, high NPLs, low diversification); Specialized banks (niche-oriented, e.g., agriculture; ROA≈1.7%; balanced portfolios); Innovative banks (private-led; ROA≈2.2%; high non-interest income, digitalization, lower NPLs).Findings partially align with state-private ownership divides but highlight private sector innovation trends. Implications: Tailored regulations to promote diversification in traditional models and enhance cyber resilience for innovative ones. Policymakers should foster tech partnerships. Future research could incorporate macroeconomic factors like inflation for longitudinal insights, aiding sustainable banking development in Iran.</OtherAbstract>
		<ObjectList>
			<Object Type="keyword">
			<Param Name="value">Banking business models</Param>
			</Object>
			<Object Type="keyword">
			<Param Name="value">Cluster analysis</Param>
			</Object>
			<Object Type="keyword">
			<Param Name="value">multidimensional financial indicators</Param>
			</Object>
			<Object Type="keyword">
			<Param Name="value">Iranian banks</Param>
			</Object>
			<Object Type="keyword">
			<Param Name="value">digital transformation</Param>
			</Object>
		</ObjectList>
</Article>
</ArticleSet>
