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

Abstract

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.

Perbandingan Fungsi Aktivasi Untuk Meningkatkan Kinerja Model LSTM Dalam Prediksi Ketinggian Air Sungai

“…2) Input Gate: Gerbang ini berperan dalam proses seleksi informasi baru yang akan disisipkan ke dalam cell state [24].…”

“…3) Output Gate: Gerbang ini melakukan proses seleksi informasi yang relevan dari cell state dan menampilkan informasi tersebut sebagai keluaran. Output gate memungkinkan LSTM untuk mengontrol informasi yang dihasilkan berdasarkan informasi pada cell state [24].…”

Penerapan Metode Recurrent Neural Network dengan Pendekatan Long Short-Term Memory (LSTM) Untuk Prediksi Harga Saham

“…Berinvestasi saham kini semakin populer dan berkembang pesat di Indonesia, dengan berinvestasi saham, investor akan mendapatkan keuntungan yang cukup cepat dan besar dalam waktu yang cukup singkat, dalam beberapa hari, minggu, bulan atau tahun dari menginvestasikan dananya [2]. Data statistik dari Kustodian Sentral Efek Indonesia (KSEI) tahun 2022 menunjukkan bahwa jumlah pertumbuhan 36 investor pasar modal semakin meningkat setiap tahunnya yakni pada akhir tahun 2022 mencapai 10,3 juta investor atau meningkat 37,68% jika dibandingkan dengan akhir tahun 2021 sebanyak 7,48 juta investor [3].…”

Next Word Prediction for Book Title Search Using Bi-LSTM Algorithm

“…C. Data Modeling Data modeling is done by implementing the Bidirectional Long Short Term Memory (Bi-LSTM) algorithm in Deep Learning. Bi-LSTM consists of two LSTM networks that have a function to process data sequences from the forward and backward directions [22]. LSTM itself will learn the data that must be removed and stored in each neuron [23].…”