Optimisasi Portfolio Mean-Conditional Value At Risk dengan Kendala Buy-In Threshold dan Kardinalitas Menggunakan Metode Artificial Bee Colony

Ratnasari, Fitria (2026) Optimisasi Portfolio Mean-Conditional Value At Risk dengan Kendala Buy-In Threshold dan Kardinalitas Menggunakan Metode Artificial Bee Colony. Other thesis, Institut Teknologi Sepuluh Nopember.

Text 5006211066_Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only Download (5MB) | Request a copy

Abstract

Penelitian ini bertujuan untuk mengembangkan model optimisasi portofolio saham LQ45 yang mampu menekan risiko kerugian ekstrem dengan menggunakan Conditional Value at Risk (CVaR) sebagai ukuran risiko utama, sekaligus mempertimbangkan kendala buy-in threshold dan kardinalitas yang mencerminkan kondisi nyata di pasar modal Indonesia. Latar belakang penelitian ini muncul dari kebutuhan investor untuk memperoleh portofolio yang tidak hanya optimal secara matematis, tetapi juga konsisten dengan aturan perdagangan dan karakteristik aset yang tersedia. Tujuan penelitian mencakup penerapan pendekatan Mean-CVaR dalam optimisasi portofolio, pemanfaatan algoritma Artificial Bee Colony (ABC) untuk memperoleh solusi optimal, serta evaluasi kinerja portofolio dari sisi risiko dan pengembalian. Penelitian menggunakan 34 saham LQ45 dengan 874 data harga penutupan harian. Optimisasi dilakukan dengan algoritma ABC, dimana fungsi objektif Mean-CVaR digunakan untuk mengukur risiko ekstrem, sementara kendala buy-in threshold dan kardinalitas dijadikan batasan dalam pembentukan portofolio. Proses optimisasi berjalan secara bertahap hingga diperoleh portofolio yang memenuhi seluruh kendala dan menyeimbangkan antara risiko dan imbal hasil. Hasil penelitian menunjukkan portofolio optimal mampu menghasilkan CVaR sebesar 0,020190 dengan return 0,068796 atau sekitar 6,88% per tahun. Kinerja portofolio dinilai dengan Sharpe Ratio sebesar 2,858897, menunjukkan bahwa portofolio mampu memberikan imbal hasil yang sepadan dengan risiko yang ditanggung. Komposisi portofolio meliputi saham CPIN, ANTM, BBCA, ITMG, dan INDF dengan bobot masing-masing 0,1084; 0,09282; 0,2578; 0,1674; dan 0,3682, seluruhnya memenuhi kendala yang ditetapkan. Kesimpulan penelitian menegaskan bahwa pendekatan Mean-CVaR yang dioptimalkan dengan algoritma ABC efektif dalam membentuk portofolio saham LQ45 yang menekan risiko ekstrem sekaligus memaksimalkan imbal hasil, sehingga dapat menjadi alat bantu yang andal dalam pengambilan keputusan investasi berbasis preferensi risiko.
================================================================================================================================
This study aims to develop a portfolio optimization model for LQ45 stocks that can mitigate extreme loss risks using Conditional Value at Risk (CVaR) as the primary risk measure, while simultaneously incorporating buy-in threshold and cardinality constraints that reflect real market conditions in Indonesia. The background of this research arises from investors’ need to construct portfolios that are not only mathematically optimal but also consistent with trading rules and asset characteristics. The objectives of this study include applying the Mean-CVaR approach in portfolio optimization, utilizing the Artificial Bee Colony (ABC) algorithm to obtain optimal solutions, and evaluating portfolio performance in terms of risk and return. The study employs 34 LQ45 stocks with 874 daily closing price data points. Optimization is carried out using the ABC algorithm, where the Mean-CVaR objective function measures extreme risk, and the buy-in threshold and cardinality constraints serve as limits in portfolio construction. The optimization process is performed iteratively until a portfolio is obtained that satisfies all constraints while balancing risk and return. The results indicate that the optimal portfolio achieves a CVaR value of 0.020190 with a return of 0.068796, equivalent to approximately 6.88% per year. Portfolio performance is evaluated using a Sharpe Ratio of 2.858897, indicating that the portfolio provides returns commensurate with the total risk undertaken. The portfolio composition includes CPIN, ANTM, BBCA, ITMG, and INDF with respective weights of 0.1084, 0.09282, 0.2578, 0.1674, and 0.3682, all of which satisfy the imposed constraints. The study concludes that the Mean-CVaR approach optimized via the ABC algorithm is effective in constructing LQ45 stock portfolios that mitigate extreme risks while maximizing returns, making it a reliable tool for investment decision-making based on investors’ risk preferences.

Item Type:	Thesis (Other)
Uncontrolled Keywords:	Artificial Bee Colony, Buy-in threshold, Conditional Value at Risk, Kardinalitas, Sharpe Ratio, Optimisasi Portofolio
Subjects:	H Social Sciences > HA Statistics H Social Sciences > HG Finance > HG4529 Investment analysis H Social Sciences > HG Finance > HG4529.5 Portfolio management H Social Sciences > HG Finance > HG4910 Investments H Social Sciences > HG Finance > HG4915 Stocks--Prices Q Science > QA Mathematics
Divisions:	Faculty of Science and Data Analytics (SCIENTICS) > Actuaria > 94203-(S1) Undergraduate Thesis
Depositing User:	Fitria Ratnasari
Date Deposited:	21 Jan 2026 07:55
Last Modified:	21 Jan 2026 07:55
URI:	http://repository.its.ac.id/id/eprint/129994

Actions (login required)

View Item