Pembentukan Portofolio Optimal Saham-Saham LQ45 Berdasarkan Sentimen Positif Menggunakan Metode DBSCAN dan Markowitz

Suputra, I Gede Dana (2025) Pembentukan Portofolio Optimal Saham-Saham LQ45 Berdasarkan Sentimen Positif Menggunakan Metode DBSCAN dan Markowitz. Jurnal Bisnis dan Kewirausahaan. ISSN 2580-5614

Text 2043211010-Article.pdf - Accepted Version Restricted to Repository staff only Download (474kB) | Request a copy

Abstract

Perkembangan pasar modal di Indonesia ditandai dengan meningkatnya jumlah investor dan perusahaan yang terdaftar di Bursa Efek Indonesia (BEI). Investor perlu mempertimbangkan berbagai informasi dalam memilih saham terbaik, salah satunya melalui berita. Melalui berita akan muncul pandangan masyarakat terhadap saham perusahaan terkait berupa pandangan positif, negatif, atau netral yang diperoleh menggunakan analisis sentimen. Media sosial X dapat menjadi sumber informasi bagi investor untuk memperoleh sentimen saham perusahaan. Penelitian ini bertujuan untuk membentuk portofolio optimal berdasarkan sentimen saham dengan metode clustering DBSCAN dan model optimasi Markowitz. Hasil penelitian menunjukkan bahwa dengan mengelompokkan saham berdasarkan rasio keuangan dan sentimen positif menggunakan DBSCAN, saham LQ45 dikelompokkan menjadi tiga cluster dan satu cluster noise. Portofolio optimal kemudian dibentuk menggunakan model Markowitz, di mana cluster noise memiliki risiko paling rendah dengan return yang sama. Temuan ini dapat membantu investor dalam menyusun strategi investasi yang lebih efektif.
======================================================================================================================================
The development of the capital market in Indonesia is marked by an increase in the number of investors and companies listed on the Indonesia Stock Exchange (IDX). Investors need to consider various types of information in selecting the best stocks, one of which is news. News can reflect public sentiment toward a company's stock in the form of positive, negative, or neutral views, which can be identified through sentiment analysis. The social media platform X can serve as a source of information for investors to obtain stock sentiment. This study aims to construct an optimal portfolio based on stock sentiment using the DBSCAN clustering method and the Markowitz optimization model. The results show that by clustering stocks based on financial ratios and positive sentiment using DBSCAN, LQ45 stocks are grouped into three clusters and one noise cluster. The optimal portfolio is then formed using the Markowitz model, where the noise cluster has the lowest risk with the same return. These findings can help investors develop more effective investment strategies.

Item Type:	Article
Additional Information:	Artikel ini belum dipublikasikan di jurnal manapun, namun direncanakan akan disubmit ke Jurnal Bisnis dan Kewirausahaan (JBK) Politeknik Negeri Bali.
Uncontrolled Keywords:	Analisis Sentimen, DBSCAN, Markowitz, Portofolio, Saham, Investasi, Pasar Modal, DBSCAN, Markowitz, Portfolio, Sentiment Analysis, Stock.
Subjects:	Q Science Q Science > Q Science (General) Q Science > Q Science (General) > Q180.55.M38 Mathematical models Q Science > QA Mathematics Q Science > QA Mathematics > QA278.55 Cluster analysis Q Science > QA Mathematics > QA76.9.D343 Data mining. Querying (Computer science) Q Science > QA Mathematics > QA278 Cluster Analysis. Multivariate analysis. Correspondence analysis (Statistics)
Divisions:	Faculty of Vocational > 49501-Business Statistics
Depositing User:	I Gede Dana Suputra
Date Deposited:	01 Sep 2025 02:53
Last Modified:	01 Sep 2025 02:53
URI:	http://repository.its.ac.id/id/eprint/119835

Actions (login required)

View Item