Simulasi Monte Carlo Untuk Optimasi Portofolio Subsektor Saham Perbankan Pada Kelompok Saham Berbasis K-Means Dengan Jarak Dynamic Time Warping (DTW)

Anwar, Muhammad Rifqy Rezvany (2026) Simulasi Monte Carlo Untuk Optimasi Portofolio Subsektor Saham Perbankan Pada Kelompok Saham Berbasis K-Means Dengan Jarak Dynamic Time Warping (DTW). Other thesis, Institute Teknologi Sepuluh Nopember.

[thumbnail of Final Laporan TA Muhammad Rifqy.pdf] Text
Final Laporan TA Muhammad Rifqy.pdf - Accepted Version
Restricted to Repository staff only

Download (3MB) | Request a copy

Abstract

Optimasi portofolio saham merupakan tantangan penting bagi investor karena harus menyeimbangkan potensi return dan risiko dalam kondisi pasar yang dinamis dan penuh ketidakpastian. Penelitian ini bertujuan untuk mengintegrasikan metode klasterisasi time series dan optimasi portofolio guna membentuk portofolio saham sektor perbankan Indonesia yang efisien. Data yang digunakan berupa harga penutupan harian saham sektor perbankan yang tercatat di Bursa Efek Indonesia pada periode 1 Juli 2023 hingga 30 September 2025 dan diperoleh dari Yahoo Finance. Pengelompokan saham dilakukan menggunakan algoritma KMeans dengan jarak Dynamic Time Warping (DTW) untuk mengidentifikasi kemiripan pola pergerakan harga historis. Hasil evaluasi menunjukkan bahwa jumlah klaster optimal adalah dua klaster dengan nilai silhouette sebesar 0,6498, yang mengindikasikan kualitas pengelompokan berada pada kategori cukup baik. Berdasarkan visualisasi pola pergerakan harga, klaster dengan karakteristik pergerakan yang relatif stabil dipilih untuk tahap analisis selanjutnya. Analisis fundamental dilakukan menggunakan indikator Return on Equity (ROE), Earning per Share (EPS), dan Price to Earnings Ratio (PER) sebagai dasar seleksi saham. Dari hasil analisis tersebut, diperoleh lima saham sektor perbankan dengan kinerja fundamental terbaik, yaitu BBCA.JK, BMRI.JK, BBRI.JK, BRIS.JK, dan BTPS.JK. Saham-saham terpilih kemudian dioptimasi menggunakan simulasi Monte Carlo dengan 5.000 pengulangan untuk memperoleh kombinasi bobot portofolio yang optimal. Hasil optimasi menunjukkan bahwa portofolio optimal memiliki kinerja yang bervariasi pada setiap periode, dengan nilai Sharpe ratio sebesar 0,8316 pada tahun 2023, 0,9499 pada tahun 2024, dan 0,9541 pada periode Year-to-Date (YTD) 2025. Temuan ini menunjukkan bahwa integrasi klasterisasi DTW, analisis fundamental, dan simulasi Monte Carlo mampu menghasilkan portofolio yang sesuai dengan dinamika pasar dan efisien dalam menyeimbangkan risiko dan return.
======================================================================================================================================
Portfolio optimization is a major challenge for investors as it requires balancing expected returns and risk under dynamic market conditions. This study aims to integrate clustering techniques and portfolio optimization to construct an efficient portfolio of Indonesian banking sector stocks. The data used consist of daily closing prices of banking stocks listed on the Indonesia Stock Exchange for the period from July 1, 2023 to September 30, 2025. Stock grouping was conducted using K-Means clustering with Dynamic Time Warping (DTW) distance to capture similarities in historical time-series price movements. The clustering evaluation results indicate that the optimal number of clusters is two, with a silhouette coefficient of 0.6498, suggesting a reasonably good clustering quality. Based on the visualization of price movement patterns, the cluster exhibiting relatively stable trends was selected for further analysis. Fundamental analysis was subsequently applied using Return on Equity (ROE), Earnings per Share (EPS), and Price to Earnings Ratio (PER) as key indicators to assess the financial soundness of the clustered stocks. This analysis identified five banking stocks with the strongest fundamental performance, namely BBCA.JK, BMRI.JK, BBRI.JK, BRIS.JK, and BTPS.JK. Portfolio optimization was then performed using a Monte Carlo simulation with 5,000 iterations to generate a wide range of possible portfolio weight combinations. Portfolio performance was evaluated using the Sharpe ratio as a risk-adjusted performance measure. The results show that the optimal portfolios exhibit varying performance across different periods, with Sharpe ratios of 0.8316 in 2023, 0.9499 in 2024, and 0.9541 in the Year-to-Date 2025 period. These findings demonstrate that the integration of DTW clustering, fundamental analysis, and Monte Carlo simulation is capable of generating a portfolio that aligns with market dynamics and efficiently balances risk and return.

Item Type: Thesis (Other)
Uncontrolled Keywords: Analisis Fundamental, Clustering, Dynamic Time Warping, Saham Perbankan, Sharpe Ratio, Simulasi Monte Carlo,Banking Stocks, Clustering, Dynamic Time Warping, Fundamental Analysis, Monte Carlo Simulation, Sharpe Ratio
Subjects: Q Science > QA Mathematics > QA276 Mathematical statistics. Time-series analysis. Failure time data analysis. Survival analysis (Biometry)
Q Science > QA Mathematics > QA278.55 Cluster analysis
Divisions: Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis
Depositing User: Muhammad Rifqy Rezvany Anwar
Date Deposited: 29 Jan 2026 08:46
Last Modified: 29 Jan 2026 08:46
URI: http://repository.its.ac.id/id/eprint/131156

Actions (login required)

View Item View Item