Claim Missing Document
Check
Articles

Found 22 Documents
Search

Model Prediksi Harga Saham BJBR Menggunakan Long Short-Term Memory (LSTM) untuk Mendukung Keputusan Investasi Susanti, Sussy; Kuraesin, Aneu
Journal of Information System, Applied, Management, Accounting and Research Vol 9 No 3 (2025): JISAMAR (Journal of Information System, Applied, Management, Accounting and Resea
Publisher : Sekolah Tinggi Manajemen Informatika dan Komputer Jayakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52362/jisamar.v9i3.2047

Abstract

Stocks are one of the most popular investment instruments among the public due to their potential for long-term returns through price appreciation and dividend distributions; however, stock price movements are heavily influenced by various factors such as macroeconomic conditions, market sentiment, and corporate actions, making accurate forecasting essential for investors to minimize risk and maximize profit. PT Bank BJB Tbk (ticker code: BJBR), a major bank in Indonesia that operates both conventional and Sharia-based services, has shown high volatility over the past few. Therefore, this research aims to develop a stock price prediction model for BJBR using the Long Short-Term Memory (LSTM) approach, a variant of Recurrent Neural Networks (RNN) well-suited for time series data. Historical closing price data from January 2020 to June 2025 were collected, preprocessed through normalization, dataset division, and transformation into supervised learning format, and then used to train an LSTM model with a two-layer architecture and dropout layers to prevent overfitting. The model was trained using the Adam optimizer and evaluated using metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared (R²). Evaluation results showed that the model achieved a high level of accuracy, with an R² value of 0.9643 on the test data, while visualizations of predicted versus actual prices demonstrated a strong alignment, proving that the LSTM model is effective in capturing temporal patterns in financial time series data and can serve as a valuable tool for data-driven investment decision-making.
Komparasi CB-SEM dan PLS-SEM dalam Mengidentifikasi Driver Kepuasan Nasabah Bank Syariah Yayu Nurhayati Rahayu; Juariah Juariah; Sussy Susanti
Journal of Management and Social Sciences Vol. 5 No. 3 (2026): August: Journal of Management and Social Sciences
Publisher : Sekolah Tinggi Ilmu Administrasi (STIA) Yappi Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study analyzes the factors influencing Islamic bank customer satisfaction in Indonesia and compares the estimation results of Covariance-Based Structural Equation Modeling (CB-SEM) and Partial Least Squares SEM (PLS-SEM). Using a quantitative survey approach, data were collected from 209 Islamic bank customers in Bandung using a 5-point Likert scale instrument. Six constructs were examined: Islamic product attributes, trust, religious commitment, service quality, customer satisfaction, and customer loyalty. CB-SEM was implemented using LISREL with Maximum Likelihood estimation, while PLS-SEM was implemented using SmartPLS 3.0 with 5,000 bootstrap subsamples. Results show that trust is the strongest determinant of customer satisfaction in both methods (PLS: β = 0.36, t = 3.80; CB-SEM: β = 0.51, t = 3.57). Religious commitment, Islamic product attributes, and service quality showed significant effects only in PLS-SEM. The satisfaction–loyalty path was not significant in either method (β = –0.21). Methodologically, PLS-SEM supported more hypotheses and produced higher convergent validity values, while CB-SEM provided more comprehensive model fit evaluation. These findings demonstrate that the two approaches are complementary rather than substitutable, and their combined use produces a more complete understanding of Islamic bank customer behavior.