Performance Comparison of Bi-LSTM and GRU for Web-Based Stock Price Prediction: A Case Study of BBCA JK

Khaerul Oktafiansyah; Muhammad Feizal

doi:10.55537/cosie.v5i4.1814

Authors

Khaerul Oktafiansyah Universitas Pamulang
Muhammad Feizal Universitas Pamulang

DOI:

https://doi.org/10.55537/cosie.v5i4.1814

Keywords:

Bi-LSTM, deep learning, Gated Recurrent Unit, Stock Prediction User Acceptance Testing

Abstract

Predicting stock prices is complex due to the non-linear and volatile characteristics of financial time-series data. This study presents a comparative analysis and web-based implementation of Bidirectional Long Short-Term Memory (Bi-LSTM) and Gated Recurrent Unit (GRU) architectures to predict the daily closing prices of PT Bank Central Asia Tbk (BBCA.JK). Using Yahoo Finance historical data from January 1, 2018, to December 31, 2024 (1,725 trading days) via a univariate approach, the dataset was partitioned into 70% training, 15% validation, and 15% testing. Empirical results demonstrate that the GRU model significantly outperforms Bi-LSTM, achieving a Root Mean Squared Error (RMSE) of 145.63, a Mean Absolute Error (MAE) of 116.95, and a Mean Absolute Percentage Error (MAPE) of 1.23%. A Paired ttest confirmed the statistical significance of this superiority, yielding a t-statistic of ???? = -4,821 and a pvalue of ???? = 0,00012 ( ???? < 0,05). The GRU model was integrated into a microservices web application using Flask API and Laravel, incorporating a rule-based Decision Support System (DSS) to provide operational trading signals (Buy, Sell, Hold) along with Take Profit and Stop Loss calculations. Evaluation via User Acceptance Testing with 21 respondents yielded a feasibility score of 82.43% ("Highly Feasible")

Downloads

Download data is not yet available.

References

[1] H. Setyawan, A. Pratama, dan R. Hidayat, "Analisis Dinamika Volatilitas Harga Saham Perbankan Blue-Chip di Bursa Efek Indonesia," J. Econ. Financ. Mark., vol. 5, no. 1, hlm. 12–21, 2024.

[2] N. P. S. Devi dan I. M. Sukartha, "Investasi Pasar Modal dan Perilaku Investor Ritel Indonesia," J. Akunt. dan Keuang. Indones., vol. 21, no. 2, hlm. 105–118, 2023.

[3] A. Hanafiah, Y. Arta, H. O. Nasution, dan Y. D. Lestari, "Penerapan Metode Recurrent Neural Network dengan Pendekatan Long Short-Term Memory (LSTM) Untuk Prediksi Harga Saham," Bull. Comput. Sci. Res., vol. 4, no. 1, hlm. 27–33, 2023, doi: 10.47065/bulletincsr.v4i1.321.

[4] R. Pratama dan D. Wijaya, "Eksplorasi Algoritma Recurrent Neural Network pada Prediksi Deret Waktu Finansial," J. Teknol. Inf. dan Komput., vol. 9, no. 2, hlm. 88–97, 2023.

[5] K. Kwanda, D. E. Herwindiati, dan M. D. Lauro, "Perbandingan LSTM dan Bidirectional LSTM pada Sistem Prediksi Harga Saham Berbasis Website," Ranah Res. J. Multidiscip. Res. Dev., vol. 7, no. 1, hlm. 26–35, 2024, doi: 10.38035/rrj.v7i1.1255.

[6] E. Novela Waroi, A. Arief, dan K. Khusnawi, "Prediksi Harga Laptop Menggunakan Algoritma GRU dan BILSTM," J. Sos. Teknol., vol. 4, no. 7, hlm. 408–424, 2024, doi: 10.59188/jurnalsostech.v4i7.1278.

[7] S. Kusworo, N. A. Santoso, dan R. D. Kurniawan, "Prediksi Nilai Akhir Semester Siswa Menggunakan Algoritma Random Forest," J. Teknoinfo, vol. 18, no. 2, hlm. 112–120, 2024.

[8] B. R. Ramadhan, M. A. D. Widyadara, dan Daniel, "Aplikasi Prediksi Harga Saham Perusahaan Dengan Menggunakan Metode Long Short Term Memory (LSTM)," J. Sains dan Inf., vol. 9, no. 1, hlm. 45–53, 2023.

[9] A. Rahmadani, B. Rahman, dan C. Azmi, "Evaluasi Metrik RMSE dan MAE dalam Pemodelan Regresi Deret Waktu," J. Sains Komput. dan Inform., vol. 8, no. 1, hlm. 33–42, 2024.

[10] K. Prayogi, W. Gata, dan D. P. Kussanti, "Prediksi Harga Saham Bank Central Asia Menggunakan Algoritma Deep Learning GRU," Jutisi J. Ilm. Tek. Inform. dan Sist. Inf., vol. 13, no. 1, hlm. 647–658, 2024, doi: 10.35889/jutisi.v13i1.1910.

[11] N. Hartono, A. A. Muin, U. Islam, dan N. Alauddin, "Penggunaan User Acceptance Testing (UAT) Pada Pengujian Sistem Informasi Pengelolaan Keuangan Dan Inventaris Barang," J. Sist. Inf. dan Teknol., vol. 7, no. 1, hlm. 15–23, 2025.

[12] R. F. Inaku dan J. C. Chandra, "Implementasi Data Mining dalam Prediksi Harga Saham Menggunakan Metode Long Short Term Memory (LSTM)," J. Tekno Komputers, vol. 12, no. 2, hlm. 101–108, 2023.

[13] A. Nugroho dan M. S. Hasibuan, "Penerapan Metode SDLC dan Pengujian Black-Box pada Pengembangan Software Berbasis Web," J. Softw. Eng. Dev., vol. 4, no. 1, hlm. 55–63, 2024.

[14] M. F. Rizky dan N. Afrianto, "Analisis Kinerja Deep Learning pada Fluktuasi Saham Berkapitalisasi Besar," J. AI dan Data Sci., vol. 3, no. 2, hlm. 89–98, 2024.

[15] F. Fitriastuti, A. E. Putri, dan A. K. Sunardi, "Analisis Website SIAKAD Universitas Janabadra Menggunakan Metode UAT," J. Inform. dan Komput., vol. 5, no. 1, hlm. 276–285, 2024.