EKSPLORASI KARAKTERISTIK SUB-SEKTOR PERBANKAN BURSA EFEK INDONESIA BERDASARKAN PROFITABILITAS, RISIKO KREDIT, DAN VALUASI SAHAM MENGGUNAKAN ALGORITMA K-MEANS CLUSTERING

    Rahmayanti Cahyaningtyas, - and Alfira Sofia, - and Budi Supriatono Purnomo, - (2025) EKSPLORASI KARAKTERISTIK SUB-SEKTOR PERBANKAN BURSA EFEK INDONESIA BERDASARKAN PROFITABILITAS, RISIKO KREDIT, DAN VALUASI SAHAM MENGGUNAKAN ALGORITMA K-MEANS CLUSTERING. S1 thesis, Universitas Pendidikan Indonesia.

    Abstract

    Penelitian ini mengeksplorasi karakteristik sub-sektor perbankan Indonesia yang terdaftar di Bursa Efek Indonesia (BEI) berdasarkan indikator profitabilitas, risiko kredit, dan valuasi saham menggunakan algoritma K-Means Clustering. Penelitian ini menggunakan data sekunder dari laporan keuangan tahunan 43 perusahaan perbankan periode 2021–2023. Analisis bertujuan untuk mengelompokkan bank ke dalam klaster dengan profil keuangan yang serupa, mengidentifikasi ciri khas masing-masing klaster, serta mengamati potensi pola perilaku bank digital. Hasil penelitian menunjukkan tiga klaster utama: (1) Konvensional Stabil, didominasi bank konvensional besar dengan posisi pasar kuat; (2) Pertumbuhan Agresif, terdiri dari bank dengan penyaluran kredit yang agresif, profitabilitas tinggi, dan risiko kredit yang cukup terkendalit; serta (3) Berisiko Tinggi, yang mayoritas berisi bank skala kecil dan berkinerja kurang baik. Penelitian juga menemukan bahwa beberapa bank digital menunjukkan pergerakan dinamis antar klaster, mencerminkan penyesuaian strategi bisnis dan adaptasi pasar yang cepat. Temuan ini memberikan wawasan bagi investor untuk memahami segmentasi sektor perbankan, tingkat risiko, dan potensi imbal hasil. Selain itu, penelitian ini berkontribusi pada literatur akademik dengan menunjukkan penerapan unsupervised machine learning dalam analisis sektor keuangan serta mendukung pengambilan keputusan investasi berbasis data. This study explores the characteristics of the Indonesian banking sub-sector listed on the Indonesia Stock Exchange (IDX) based on profitability, credit risk, and stock valuation indicators using the K-Means Clustering algorithm. The research utilizes secondary data obtained from the annual financial statements of 43 banking companies for the 2021–2023 period. The analysis aims to classify banks into clusters with similar financial profiles, identify the distinctive characteristics of each cluster, and examine potential behavioral patterns among digital banks. The results reveal three primary clusters: (1) Konvensional Stabil, dominated by large conventional banks with strong market positions; (2) Pertumbuhan Agresif, consisting of banks with aggressive credit expansion, high profitability, and moderate credit risk; and (3) Berisiko Tinggi, predominantly composed of small-scale banks with weaker performance. The study also finds that several digital banks demonstrate dynamic movements between clusters, reflecting rapid adjustments in business strategies and market adaptation. These findings offer valuable insights for investors in understanding banking sector segmentation, associated risk levels, and potential returns. Furthermore, the study contributes to the academic literature by demonstrating the application of unsupervised machine learning in financial sector analysis and supporting data-driven investment decision-making.

    Baca Full Text klik disini
    [thumbnail of S_PEA_2103526_Title.pdf] Text
    S_PEA_2103526_Title.pdf
    Download (548kB)
    [thumbnail of S_PEA_2103526_Chapter 1.pdf] Text
    S_PEA_2103526_Chapter 1.pdf
    Download (172kB)
    [thumbnail of S_PEA_2103526_Chapter 2.pdf] Text
    S_PEA_2103526_Chapter 2.pdf
    Restricted to Staf Perpustakaan
    Download (318kB)
    [thumbnail of S_PEA_2103526_Chapter 3.pdf] Text
    S_PEA_2103526_Chapter 3.pdf
    Download (183kB)
    [thumbnail of S_PEA_2103526_Chapter 4.pdf] Text
    S_PEA_2103526_Chapter 4.pdf
    Restricted to Staf Perpustakaan
    Download (527kB)
    [thumbnail of S_PEA_2103526_Chapter 5.pdf] Text
    S_PEA_2103526_Chapter 5.pdf
    Download (42kB)
    [thumbnail of S_PEA_2103526_Appendix.pdf] Text
    S_PEA_2103526_Appendix.pdf
    Restricted to Staf Perpustakaan
    Download (393kB)
    Official URL: https://repository.upi.edu
    Item Type: Thesis (S1)
    Additional Information: ID SINTA Dosen Pembimbing: Alfira Sofia: 259602 Budi Supriatono Purnomo: 5996343
    Uncontrolled Keywords: K-Means Clustering, profitabilitas, risiko kredit, valuasi saham, sektor perbankan K-Means Clustering, profitability, credit risk, stock valuation, banking sector
    Subjects: H Social Sciences > HF Commerce > HF5601 Accounting
    H Social Sciences > HG Finance
    L Education > L Education (General)
    Divisions: Fakultas Pendidikan Ekonomi dan Bisnis > Akuntansi (non kependidikan)
    Depositing User: Rahmayanti Cahyaningtyas
    Date Deposited: 27 Oct 2025 08:04
    Last Modified: 27 Oct 2025 08:04
    URI: http://repository.upi.edu/id/eprint/143264

    Actions (login required)

    View Item View Item