Prediksi Return Saham Perbankan dengan Metode LSTM dan Estimasi Value at Risk dengan Copula Ali-Mikhail-Haq Menggunakan Korelasi Kendall's Tau
Submission Date: 2024-07-29 09:29:19
Accepted Date: 2025-05-05 00:00:00
Abstract
Prediksi return saham dan estimasi Value at Risk (VaR) adalah hal yang penting dalam pengelolaan portofolio investasi. Metode LSTM telah menunjukkan potensi untuk prediksi harga saham yang akurat, sementara Copula Ali-Mikhail-Haq dengan korelasi Kendall's Tau digunakan untuk mengatasi distribusi non-normal dalam estimasi VaR. Penelitian ini bertujuan untuk menerapkan metode LSTM dalam prediksi return saham periode 2021-2023 dan estimasi VaR menggunakan Copula Ali-Mikhail-Haq dengan korelasi Kendall's Tau pada saham perbankan. Berdasarkan hasil penelitian, metode LSTM menunjukkan model terbaik untuk saham BMRI dengan konfigurasi 100 epoch, 64 unit, dan dropout sebesar 0,1 serta menghasilkan MAE sebesar 0,0174. Sedangkan untuk saham BBRI, model terbaik memiliki konfigurasi yang sama tetapi dengan dropout sebesar 0,2 menghasilkan MAE sebesar 0,0222. Secara keseluruhan, model LSTM menunjukkan kemampuan yang baik dalam memprediksi harga dan return saham. Dalam estimasi VaR, diperoleh koefisien Kendall's Tau sebesar 0,0676 dan estimasi parameter Copula Ali-Mikhail-Haq sebesar 0,281. Estimasi VaR portofolio saham pada tingkat kepercayaan 99%, 95%, dan 90% berturut-turut adalah -0,03001060; -0,01875786; dan -0,01350327.. Hasil analisis ini memberikan pemahaman yang lebih baik tentang prediksi return saham menggunakan LSTM dan estimasi VaR menggunakan Copula Ali-Mikhail-Haq.
Keywords
Asuransi Umum; Bootstrapping; Cadangan IBNR; Mack Chain Ladder
CC Licencing
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under a Creative Commons Attribution License that allows others to share the work with an acknowledgement of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgement of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (See The Effect of Open Access).
Refbacks
- There are currently no refbacks.

Jurnal Sains dan Seni ITS by Lembaga Penelitian dan Pengabdian Kepada Masyarakat, LPPM-ITS is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Based on a work at https://ejurnal.its.ac.id/index.php/sains_seni.