View Item 
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - School of Data Science, Mathematic and Informatics
      • UT - Statistics and Data Sciences
      • View Item
      •   IPB Repository
      • Dissertations and Theses
      • Undergraduate Theses
      • UT - School of Data Science, Mathematic and Informatics
      • UT - Statistics and Data Sciences
      • View Item
      JavaScript is disabled for your browser. Some features of this site may not work without it.

      Optimasi Portofolio Saham Jakarta Islamic Index 70 dengan Model Markowitz berbasis Penggerombolan Deret Waktu K-Medoids

      Thumbnail
      View/Open
      Cover (541.4Kb)
      Fulltext (2.163Mb)
      Lampiran (507.7Kb)
      Date
      2026
      Author
      Harkaputra, Muhammad Hafizd
      Oktarina, Sachnaz Desta
      Susetyo, Budi
      Metadata
      Show full item record
      Abstract
      Keberagaman pilihan emiten saham pada JII70 menawarkan berbagai opsi dalam pengambilan keputusan investasi. Namun, sifat fluktuasi dan kompleksitas informasi harga saham memperbesar risiko investasi sehingga diperlukan metode yang robust dan dapat meminimumkan risiko dalam pembentukan portofolio investasi. Penelitian ini mengevaluasi kinerja portofolio saham JII70 dengan mengintegrasikan penggerombolan deret waktu dalam pembentukan portofolio dan model optimasi dalam penentuan alokasi bobot optimum portofolio. Metode K-medoids dengan ukuran jarak DTW mampu mengelompokkan saham berdasarkan kemiripan karakteristik harga guna mereduksi kompleksitas informasi sebelum pembentukan portofolio. Penggerombolan dilakukan dengan skema standardisasi dan tanpa standardisasi. Portofolio dibentuk dengan kombinasi emiten setiap gerombol, kemudian dioptimasi menggunakan model Markowitz untuk menentukan bobot optimum emiten yang meminimumkan risiko setiap portofolio. Studi kasus dilakukan pada 46 emiten JII70 yang dipetakan ke dalam 4 gerombol optimum. Pembentukan portofolio berdasarkan kombinasi emiten dari setiap gerombol terbentuk menghasilkan 280 portofolio pada skema dengan standardisasi dan 936 portofolio pada skema tanpa standardisasi. Hasil optimasi model Markowitz pada setiap portofolio menunjukkan bahwa portofolio terbaik dengan skema penggerombolan tanpa standardisasi memberikan hasil diversifikasi yang efektif dibandingkan skema penggerombolan dengan standardisasi dan skema tanpa penggerombolan. Nilai Sharpe ratio sebesar 1.01 yang lebih tinggi serta risiko mingguan sebesar 3.02% yang lebih rendah dibandingkan skema lainnya merefleksikan keunggulan skema penggerombolan tanpa standardisasi dalam menghasilkan kinerja portofolio yang lebih baik.
       
      The diversity of stocks within the JII70 index offers various options for investment decision-making. However, the fluctuating characteristic and complexity of stock price information raise investment risk, requiring a robust method capable of minimizing risk portfolio construction. This study elevates the performance of JII70 stock portfolios by integrating time-series clustering for portfolio formation and an optimization model for determining optimum stock weight allocation to minimizing the risk. The K-Medoids method with DTW distance applied to cluster stocks based on characteristic similarity, aiming to reduce information complexity prior for portfolio construction. Clustering was performed using two schemes: with standardization and without standardization. Portfolio were constructed using combinations of stocks from each cluster, the optimized using the Markowitz model to determine the optimum weights that minimize the risk of each portfolio. The case was conducted on 46 JII70 stocks, which mapped into 4 optimum clusters. Portfolio construction based on stocks combination from each cluster resulted in 280 portfolios for standardized scheme and 936 portfolios for non-standardized scheme. The Markowitz optimization results indicated that the best portfolio from the non-standardized clustering scheme provided effective diversification and compared to the standardized clustering scheme and non-clustered scheme. A higher Sharpe ratio of 1.01 and a lower weekly risk of 3.02% compared to other schemes reflect the superiority of non-standardized clustering scheme in generating better portfolio.
       
      URI
      http://repository.ipb.ac.id/handle/123456789/172006
      Collections
      • UT - Statistics and Data Sciences [86]

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository
        

       

      Browse

      All of IPB RepositoryCollectionsBy Issue DateAuthorsTitlesSubjectsThis CollectionBy Issue DateAuthorsTitlesSubjects

      My Account

      Login

      Application

      google store

      Copyright © 2020 Library of IPB University
      All rights reserved
      Contact Us | Send Feedback
      Indonesia DSpace Group 
      IPB University Scientific Repository
      UIN Syarif Hidayatullah Institutional Repository
      Universitas Jember Digital Repository