Sianipar, Reza (2023) Estimasi Risiko Portofolio Optimal Model Mean Absolute Deviation Menggunakan Monte Carlo Berdasarkan Prediksi Harga Saham Dengan Double Exponential Smoothing. Other thesis, Institut Teknologi Sepuluh Nopember.
![[thumbnail of 06311940000025-Undergraduate_Thesis.pdf]](http://repository.its.ac.id/style/images/fileicons/text.png) |
Text
06311940000025-Undergraduate_Thesis.pdf - Accepted Version Restricted to Repository staff only until 1 October 2025. Download (2MB) | Request a copy |
Abstract
Dalam investasi saham, terdapat dua hal yang menjadi pertimbangan bagi para investor, yaitu tingkat pengembalian (return) dan tingkat risiko. Pada umumnya, hal yang dilakukan investor untuk mengurangi tingkat risiko dan mengoptimalkan return saat berinvestasi adalah membentuk portofolio. Saat investor mengambil keputusan dalam pembentukan portofolio dan berinvestasi di kemudian hari, diperlukan suatu pemodelan untuk memprediksi harga saham dan mengestimasi tingkat risiko. Oleh karena itu, investor memerlukan ukuran pasti yang dapat menentukan besarnya risiko yang akan diperoleh sehingga pada penelitian ini dilakukan perhitungan estimasi risiko portofolio optimal model Mean Absolute Deviation (MAD) menggunakan Monte Carlo berdasarkan prediksi harga saham dengan Double Exponential Smoothing. Data yang digunakan adalah data harga penutupan (closing price) harian saham yang konsisten tergabung dalam indeks SRI-KEHATI periode April 2019-November 2022 selama tiga tahun (1 April 2019–31 Maret 2022). Hasil penelitian menunjukkan bahwa peramalan harga saham SRI-KEHATI untuk periode 10 hari kedepan dengan menggunakan metode Double Exponential Smoothing menghasilkan nilai error (MAPE) yang rendah yaitu <10% yang artinya hasil peramalan harga saham dapat dikatakan sangat baik. Kemudian, portofolio yang dibentuk berdasarkan data harga saham aktual dan peramalan menggunakan model portofolio optimal Mean Absolute Deviation (MAD) menghasilkan 7 saham penyusun portofolio yaitu BBCA, BBRI, BSDE, INDF, KLBF, TLKM, dan UNTR. Hasil perhitungan estimasi risiko portofolio MAD berdasarkan Value at Risk (VaR) dan Conditional Value at Risk (CVaR) yang disimulasikan dengan Monte Carlo pada tingkat kepercayaan 95% memiliki nilai masing-masing sebesar 4,20% dan 5,67%. Tingkat risiko portofolio ini lebih rendah jika dibandingkan dengan saham penyusunnya. Selanjutnya, nilai VaR portofolio yang telah didapatkan dengan tingkat kepercayaan 95% tidak dapat mengestimasi risiko portofolio dengan baik. Hal ini berkaitan dengan keterbatasan metode VaR dalam mengestimasi kerugian yang melebihi nilai VaR itu sendiri. Untuk mengatasi kelemahan tersebut, investor dapat menggunakan nilai CVaR sebagai alternatif dalam mengukur risiko investasi portofolio agar dapat mengetahui estimasi nilai kerugian di atas nilai VaR.
==================================================================================================================================
In stock investment, there are two things that are considered for investors, namely the rate of return (return) and the level of risk. In general, what investors do to reduce the level of risk and optimize returns when investing is to form a portfolio. When investors make decisions in portfolio formation and invest in the future, modeling is needed to predict stock prices and estimate the level of risk. Therefore, investors need a definite measure that can determine the amount of risk to be obtained so that in this study the calculation of optimal portfolio risk estimation of the Mean Absolute Deviation (MAD) model using Monte Carlo based on stock price predictions with Double Exponential Smoothing. The data used is daily closing price data of stocks that are consistently incorporated in the SRI-KEHATI index for the period April 2019-November 2022 for three years (April 1, 2019-March 31, 2022). The results showed that SRI-KEHATI's stock price forecasting for the next 10 days using the Double Exponential Smoothing method resulted in a low error value (MAPE), <10% which means that the stock price forecasting results can be said to be very good. Then, a portfolio formed based on actual stock price data and forecasting using the optimal portfolio model Mean Absolute Deviation (MAD) produces 7 portfolio constituent stocks, namely BBCA, BBRI, BSDE, INDF, KLBF, TLKM, and UNTR. The results of the calculation of MAD portfolio risk estimates based on Value at Risk (VaR) and Conditional Value at Risk ( CVaR) simulated with Monte Carlo at a 95% confidence level have values of 4,20% and 5,67% respectively. The risk level of this portfolio is lower when compared to its constituent stocks. Furthermore, the portfolio VaR value that has been obtained with a 95% confidence level cannot estimate portfolio risk properly. This is related to the limitations of the VaR method in estimating losses that exceed the value of VaR itself. To overcome these weaknesses, investors can use the CVaR value as an alternative in measuring portfolio investment risk in order to find out the estimated loss value above the VaR value.
| Item Type: | Thesis (Other) |
|---|---|
| Uncontrolled Keywords: | Conditional Value at Risk, Double Exponential Smoothing, Mean Absolute Deviation, Portofolio, Monte Carlo |
| Subjects: | H Social Sciences > HA Statistics > HA30.3 Time-series analysis H Social Sciences > HB Economic Theory > Economic forecasting--Mathematical models. H Social Sciences > HG Finance H Social Sciences > HG Finance > HG4012 Mathematical models H Social Sciences > HG Finance > HG4529 Investment analysis H Social Sciences > HG Finance > HG4529.5 Portfolio management H Social Sciences > HJ Public Finance |
| Divisions: | Faculty of Science and Data Analytics (SCIENTICS) > Actuaria > 94203-(S1) Undergraduate Thesis |
| Depositing User: | Reza Sianipar |
| Date Deposited: | 02 Aug 2023 01:52 |
| Last Modified: | 02 Aug 2023 01:52 |
| URI: | http://repository.its.ac.id/id/eprint/100310 |
Actions (login required)
 |
View Item |