ANALISIS KARAKTERISTIK CLUSTER SAHAM DENGAN RETURN DI ATAS 50% MENGGUNAKAN METODE K-MEANS CLUSTERING BERDASARKAN KINERJA KEUANGAN PADA PERUSAHAAN di BURSA EFEK INDONESIA PERIODE 2023-2025

Salim, Susan Ratna (2026) ANALISIS KARAKTERISTIK CLUSTER SAHAM DENGAN RETURN DI ATAS 50% MENGGUNAKAN METODE K-MEANS CLUSTERING BERDASARKAN KINERJA KEUANGAN PADA PERUSAHAAN di BURSA EFEK INDONESIA PERIODE 2023-2025. Tesis (S2) - thesis, Universitas Bakrie.

	Text (Cover) 00. Cover.pdf - Accepted Version Download (742kB)
	Text (Bab 1 - 3) 01. BAB I-III.pdf - Accepted Version Restricted to Registered users only Download (1MB) | Request a copy
	Text (Bab 4) 02. Bab IV.pdf - Accepted Version Restricted to Registered users only Download (1MB) | Request a copy
	Text (Bab 5) 03. Bab V.pdf - Accepted Version Restricted to Registered users only Download (403kB) | Request a copy
	Text (Daftar Pustaka) 04. Daftar Pustaka.pdf - Accepted Version Download (330kB)

Abstract

This research aim to analyze the clustering of stocks with returns above 50% among companies listed on the Indonesia Stock Exchange (IDX) during the 2023–2025 period based on financial performance characteristics, identify the characteristics and dominant cluster, and develop a prototype. This quantitative study applies the K-Means Clustering method to 34 issuers. The research variables include Return on Equity (ROE), Net Profit Margin (NPM), Earnings Per Share (EPS), Price to Earnings Ratio (PER), Price to Book Value (PBV), Debt to Equity Ratio (DER), and Compound Annual Growth Rate (CAGR). The data were processed using Winsorizing and Robust Scaling. The number of clusters was determined a priori by setting three clusters and subsequently evaluated using the Elbow Method, Silhouette Coefficient (SC), Davies–Bouldin Index (DBI), and Calinski–Harabasz Index (CHI). Clustering consistency was verified by repeating the analysis using the same settings and changing the order of observations. The results indicate three clusters: Cluster 1 (Aggressive) with high profitability, growth, and leverage; Cluster 2 (Contractive) with negative profitability and growth and moderate leverage; and Cluster 3 (Conservative) with moderately positive profitability and growth and low leverage. Cluster 3 is dominant, comprising 26 issuers (76.47%), and is dominated by the Properties sector, particularly Real Estate Development & Management. The clustering results can support investor risk appetite mapping. A prototype based on Euclidean Distance was developed using the final cluster centers to map new issuers based on the similarity of seven financial variables. The results show that stocks with returns above 50% have diverse financial characteristics and can be grouped based on profitability, growth, valuation, earnings-generating ability, and capital structure.

Item Type:	Thesis (Tesis (S2) - )
Uncontrolled Keywords:	K-Means Clustering, return saham, risk appetite, Euclidean Distance, prototype.
Subjects:	Finance > Finance Management Finance > Investment > Stockbrokers > Investment advisers Finance > Investment > Stockbrokers Thesis > Thesis (S2)
Divisions:	Fakultas Ekonomi dan Ilmu Sosial > Program Studi Magister Management
Depositing User:	Susan Ratna Salim
Date Deposited:	14 Sep 2026 07:56
Last Modified:	14 Sep 2026 07:56
URI:	https://repository.bakrie.ac.id/id/eprint/14601

Actions (login required)

View Item