Institutional Repository UIN Sunan Kalijaga YogyakartaANALISIS RISIKO SAHAM SYARI’AH MENGGUNAKAN METODE LONG SHORT-TERM MEMORY (LSTM) DENGAN PENDEKATAN VALUE AT-RISK (VaR)NIM.: 21106010079Nur Aisyiah JamilauthorThis study aims to analyze investment risk in Islamic stocks by applying the Long Short-Term Memory (LSTM) method and the Value at-Risk (VaR) approach. The research objects include the stocks of PT Aneka Tambang Tbk (ANTM) and PT Bumi Resources Minerals Tbk (BRMS), which are listed in the Indonesian Sharia Stock Index (ISSI). These stocks were selected because gold prices in Indonesia have tended to increase over several periods, thereby generating positive sentiment toward gold mining stocks. In addition, the price data exhibit more upward movements than declines, making them suitable for further analysis. The data used consist of daily closing prices from June 5, 2023, to May 28, 2025, obtained from the Indonesia Stock Exchange (IDX). The LSTM model is employed to predict stock price movements based on historical patterns using variations in the number of neurons (5, 10, and 20), epochs (50 and 100), and optimizers (RMSprop, Adam, and AdamW). Model performance is evaluated using Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Error (MAE). The evaluation results show that the MAE values for the analyzed stocks are below 0.05, indicating good predictive performance. Furthermore, investment risk is analyzed using the Value at Risk (VaR) method through the Monte Carlo simulation approach, which is categorized as a non-parametric method. The validation test using the Likelihood Ratio (LR) indicates that the VaR estimates for 7-day and 30-day horizons are inaccurate, as the LR values exceed 3.841, while the 1-day VaR is considered accurate because the LR value is below 3.841. This study is conducted based on the consideration that investment in Islamic stocks should not only focus on returns but also take into account the potential risks involved. Overall, the results demonstrate that the combination of LSTM and VaR methods is effective in predicting stock price movements and measuring the level of investment risk in Islamic stocks.310 Statistik658.15 Manajemen Keuangan2026-01-29UIN SUNAN KALIJAGA YOGYAKARTA;FAKULTAS SAINS DAN TEKNOLOGIThesis

For work being deposited by its own author: In self-archiving this collection of files and associated bibliographic metadata, I grant Institutional Repository UIN Sunan Kalijaga Yogyakarta the right to store them and to make them permanently available publicly for free on-line. I declare that this material is my own intellectual property and I understand that Institutional Repository UIN Sunan Kalijaga Yogyakarta does not assume any responsibility if there is any breach of copyright in distributing these files or metadata. (All authors are urged to prominently assert their copyright on the title page of their work.)

For work being deposited by someone other than its author: I hereby declare that the collection of files and associated bibliographic metadata that I am archiving at Institutional Repository UIN Sunan Kalijaga Yogyakarta) is in the public domain. If this is not the case, I accept full responsibility for any breach of copyright that distributing these files or metadata may entail.

Clicking on the deposit button indicates your agreement to these terms.