Abdillah, Ahmad Reyhan (2023) Optimasi Portofolio Saham Indeks SRI-KEHATI dengan Metode Modern Portfolio Theory dan Metaheuristic Berdasarkan Harga Saham Historis dan Hasil Ramalan Long Short-Term Memory. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 06211940000095-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
06211940000095-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2025. Download (9MB) | Request a copy |
Abstract
Besarnya pasar modal serta banyaknya investor di lantai bursa Indonesia membuat optimasi portofolio dapat menjadi suatu concern penting di kalangan para pelaku bursa efek Indonesia mengingat pembentukan portofolio diperlukan sebagai suatu diversifikasi untuk meminimalisir risiko investasi. Indeks SRI-KEHATI dapat menjadi acuan optimasi portfolio saham mengingat indeks tersebut menjadi salah satu indeks teraktif di Bursa Efek Indonesia dalam hal volume transaksi saham serta implementasi bidang Environmental, Social, and Governance (ESG) yang sesuai dengan konsep Ekonomi Hijau. Oleh karena itu, berikut dilakukan analisis optimasi portofolio dari saham-saham yang terdapat pada indeks SRI-KEHATI dengan metode optimasi Model Markowitz dan Simulasi Monte Carlo sebagai metode dari Modern Portfolio Theory yang memiliki efektivitas dalam hal meminimalisir risiko dan menangkap berbagai kemungkinan hasil serta GA dan PSO sebagai metode metaheuristic atau prosedur non-gradient based untuk menemukan global optima yang dianggap lebih efisien dikarenakan penyelesaiannya telah tercakup ke dalam satu algoritma. Selain itu, optimasi portofolio juga dilakukan terhadap data hasil ramalan dari metode Long Short-Term Memory yang mampu mengenali long-term dependencies dari data sehingga sesuai dengan peramalan harga saham dengan perioda data jangka panjang. Data harga saham yang digunakan pada seluruh emiten yaitu data harga saham penutupan pada rentang tanggal 4 Januari 2021 hingga 28 Februari 2023 dengan pembagian 95% data awal digolongkan sebagai data historis sedangkan 5% lainnya dijadikan sebagai benchmark dari hasil ramalan. Peramalan harga saham dengan metode LSTM memperoleh nilai MAPE hasil ramalan yang berada pada rentang 1% hingga 12% atau dapat diintpretasikan bahwa model-model LSTM dari emiten-emiten anggota indeks SRI-KEHATI memiliki keakurasian baik hingga sangat baik dalam hal meramalkan harga saham. Pada optimasi portofolio, portofolio optimum berdasarkan data harga saham historis memperoleh dua metode terbaik yang berbeda pada data training dan testing, yaitu Particle Swarm Optimization dan Simulasi Monte Carlo. Pada portofolio optimum berdasarkan data hasil ramalan, diperoleh bahwa metode Particle Swarm Optimization menjadi metode terbaik dengan nilai Sharpe ratio tertinggi pada data training maupun testing.
===============================================================================================================================
The size of the capital market and the large number of investors on the Indonesian stock exchange make portfolio optimization become an important concern among Indonesian stock exchange stakeholders, considering that portfolio formation is required as a form of diversification to minimize invetsment risk. The SRI-KEHATI indeks can be used as a reference for stock portfolio optimization considering that SRI-KEHATI indeks is one of the most active indexes on the Indonesia Stock Exchange in terms of stock transaction volume and the implementation of the Environmental, Social, and Governance (ESG) sector in accordance with the Green Economy concept. Therefore, the following is a portfolio optimization analysis of the stocks contained in the SRI-KEHATI index using the Markowitz Model optimization and Monte Carlo Simulation as the methods from Modern Portfolio Theory which has effectiveness in terms of minimizing risk and capturing various possible outcomes as well as GA and PSO are the metaheuristic methods or the non-gradient based procedures for finding global optima which are considered more efficeint because the solution has been included in one algorithm. In addition, portfolio optimization is also carried out on forecast result data from the Long Short-Term Memory method which is able to recognize long-term dependencies of the data so that it is in accordance with stock price forecasting with long-term data periods. The stock price data used for all issuers, specifically closing stock price data in the range of Januari 4th, 2021 to February 28th, 2023 with a partition of 95% of the initial data are classified as historical data while the other 5% are used as a benchmark from forecast results. Forecasting stock prices uting the LSTM method obtains forecasted MAPE values that span in the range of 1% up to 12% or it can be interpreted that the LSTM models of issuers that are members of the SRI-KEHATI index have good to very good accuracy in terms of predicting stock prices. In portfolio optimization, optimum portfolio based on historical stock price data obtains two different best methods on training and testing data, namely Particle Swarm Optimization and Monte Carlo Simulation. In the optimum portfolio based on forecast data, it is found that the Particle Swarm Optimization method is the best method with the highest Sharpe ratio value on both training and testing data.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Long Short-Term Memory, Metaheuristic, Modern Portfolio Theory, Optimasi Portofolio, SRI-KEHATI, Long Short-Term Memory, Metaheuristic, Modern Portfolio Theory, Portfolio Optimization |
| Subjects: | H Social Sciences > HA Statistics > HA30.3 Time-series analysis H Social Sciences > HG Finance > HG4529.5 Portfolio management Q Science > Q Science (General) > Q325.5 Machine learning. Support vector machines. Q Science > Q Science (General) > Q337.3 Swarm intelligence |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Statistics > 49201-(S1) Undergraduate Thesis |
| Depositing User: | Ahmad Reyhan Abdillah |
| Date Deposited: | 06 Sep 2023 04:34 |
| Last Modified: | 06 Sep 2023 04:34 |
| URI: | http://repository.its.ac.id/id/eprint/104394 |
Actions (login required)
 |
View Item |