Optimasi Portofolio Saham Indeks SRI-KEHATI Menggunakan Cardinality Constrained Mean Variance dan Algoritma Metaheuristik

Nur Ihzza, Juwita (2025) Optimasi Portofolio Saham Indeks SRI-KEHATI Menggunakan Cardinality Constrained Mean Variance dan Algoritma Metaheuristik. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 2043221066-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (7MB) | Request a copy

Abstract

Meningkatnya kesadaran investor terhadap aspek keberlanjutan mendorong perlunya pendekatan optimasi portofolio yang lebih realistis, khususnya dalam mempertimbangkan kendala jumlah saham. Penelitian ini menggunakan fungsi objektif Cardinality Constrained Mean Variance (CCMV), menambahkan kendala kardinalitas sehingga meningkatkan kompleksitas proses optimasi, yang diatasi melalui pendekatan algoritma metaheuristik Particle Swarm Optimization (PSO) dan Artificial Bee Colony (ABC). Data penelitian terdiri dari 25 saham Indeks SRI-KEHATI pada periode 3 Maret 2025 hingga 29 Agustus 2025, dengan tahapan analisis meliputi eliminasi saham berdasarkan risk-free rate (RFR), optimasi portofolio, serta evaluasi kinerja menggunakan expected return, risiko, dan nilai Sharpe. Hasil penelitian menunjukkan bahwa PSO menghasilkan portofolio dengan 8 saham dan nilai Sharpe sebesar 27,594%, sedangkan ABC menghasilkan portofolio dengan 9 saham dan nilai Sharpe tertinggi sebesar 27,599%. Meskipun selisih nilai Sharpe relatif kecil, ABC menunjukkan kinerja yang lebih unggul dibandingkan PSO, baik dari nilai sharpe maupun efisiensi komputasi, yang didukung oleh mekanisme eksplorasi dan pembaruan solusi melalui fase employed bee, onlooker bee, dan scout bee. Berdasarkan hasil tersebut, ABC ditetapkan sebagai algoritma terbaik dalam membentuk portofolio optimal pada Indeks SRI-KEHATI. Sebagai implikasi praktis, penelitian ini mengembangkan dashboard optimasi portofolio berbasis Streamlit yang menampilkan proses eliminasi saham, hasil optimasi, visualisasi efficient frontier, serta alokasi bobot portofolio sebagai alat bantu pengambilan keputusan investasi berkelanjutan yang dapat diakses melalui tautan optimasiabc.streamlit.app.
==============================================================================================================================
Increased investor awareness of sustainability aspects has prompted the need for a more realistic portfolio optimisation approach, particularly when considering share quantity constraints. This study uses the Cardinality Constrained Mean-Variance (CCMV) objective function, adding cardinality constraints that increase the complexity of the optimisation process, which is overcome through the metaheuristic algorithm approaches of Particle Swarm Optimisation (PSO) and Artificial Bee Colony (ABC). The research data consists of 25 SRI-KEHATI Index stocks for the period from 3 March 2025 to 29 August 2025, with analysis stages including stock elimination based on the risk-free rate (RFR), portfolio optimisation, and performance evaluation using expected return, risk, and Sharpe value. The results show that PSO produces a portfolio of 8 stocks with a Sharpe ratio of 27.594%, while ABC produces a portfolio of 9 stocks with the highest Sharpe ratio of 27.599%. Although the difference in Sharpe value is relatively small, ABC shows superior performance compared to PSO, both in terms of solution quality and computational efficiency, supported by the mechanism of exploration and solution updating through the employed bee, onlooker bee, and scout bee phases. Based on these results, ABC was determined to be the best algorithm for forming an optimal portfolio on the SRI-KEHATI Index. As a practical implication, this study developed a Streamlit-based portfolio optimisation dashboard that displays the stock elimination process, optimisation results, efficient frontier visualisation, and portfolio weight allocation as a tool to assist in sustainable investment decision-making, which can be accessed via the link optimasiabc.streamlit.app.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Artificial Bee Colony, Cardinality Constrained Mean Variance, Metaheuristik, Particle Swarm Optimization, SRI-KEHATI, Artificial Bee Colony, Cardinality Constrained Mean Variance, Metaheuristic, Particle Swarm Optimization, SRI-KEHATI
Subjects:	H Social Sciences > HG Finance H Social Sciences > HG Finance > HG4529 Investment analysis H Social Sciences > HG Finance > HG4529.5 Portfolio management H Social Sciences > HG Finance > HG4910 Investments Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > Q Science (General) > Q337.3 Swarm intelligence T Technology > T Technology (General) > T57.84 Heuristic algorithms.
Divisions:	Faculty of Vocational > 49501-Business Statistics
Depositing User:	Juwita Nur Ihzza
Date Deposited:	29 Dec 2025 05:37
Last Modified:	29 Dec 2025 05:37
URI:	http://repository.its.ac.id/id/eprint/129167

Actions (login required)

View Item