Implementasi Long Short Term Memory (LSTM) dan Bidirectional Long Short Term Memory (BiLSTM) Dalam Prediksi Harga Saham Syariah

The development of the stock market in Indonesia is currently growing quite rapidly. This can be seen based on the number of investors who have increased every year. In 2011, sharia stocks were launched for the first time in Indonesia, and it can be seen that the price of the stock is not always stable or can experience increases or decreases. For investors, a strategy is needed to predict stock prices in order to make the right decisions in investing. In this study, stock prediction was carried out using the Long Short-Term Memory (LSTM) and Bidirectional Long Short-Term Memory (BiLSTM) methods. The data used in this study is historical closing price data for three Sharia stocks, namely PT Aneka Tambang Tbk, PT Unilever Indonesia Tbk, and PT Indofood Sukses Makmur Tbk. In building the best predictive model in this study based on tuning parameters such as epoch, batch, neurons, as well as an optimizer and dropout regulation techniques to prevent overfitting of the model. The test results show that from the three stock data used, the smallest MAPE value is obtained in the BiLSTM model. The MAPE values obtained for each stock data in this study are sequentially 2,59%, 1,77%, and 1,05%. Based on the MAPE value criteria, the prediction model is included in the very accurate criteria.