Article Per Year (5 Year)
p-Index From 2021 - 2026
0.408
P-Index
This Author published in this journals
All Journal Jurnal Informatika Ekonomi Bisnis Jurnal Informatika Ekonomi Bisnis
Sanudin
Informatics Engineering Department, Universitas Pelita Bangsa
Economics, Econometrics & Finance

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

 1 
Comparative Analysis of LSTM and GRU Models for Predicting BBCA and BBNI Stock Prices Muhammad Irfansyah; Dendy K Pramudito; Sanudin
Jurnal Informatika Ekonomi Bisnis Vol. 8, No. 2 (June 2026)
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/infeb.v8i2.1467

Abstract

Stock price predictions always a challenging issue as the price data consists of variable, noisy, non-linear time dependence. This research aims as a testing ground to compare the performance of two deep learning algorithms, long short-term memory and gated recurrent units, in predicting the end price of PT Bank Central Asia Tbk, that is relatively stable compares to PT Bank Negara Indonesia Tbk which more volatile. Daily prices were obtained from Yahoo Finance over the previous period from January1, 2019 until Dec 1, 2025. Data cleaning, Min-Max normalization, 80:20 data split, and sequence-formation with a timestep of 60 were performed. To facilitate fair comparison and ensure that the performance differences are only due to architecture, both models were constructed with the same architecture (two layers of 50 units, 0.2 dropout, Adam optimizer, MSE loss function, and 50 epochs). It evaluated MSE, RMSE performance, MAE performance, R-squared with accuracy adjusted for a 5% tolerance range. The results suggest that GRU outperforms LSTM on both stocks. For the BBCA, GRU reached an RMSE of 101.12, MAE of 113.82, R-squared of 0.96, and tolerance accuracy of 98.52%, compared to BBNI which had an RMSE of 62.95, MAE of 71.24, R-squared of 0.92, and tolerance accuracy of 94.11%. This performance led us to realize that GRU is the numerical equivalent to this technique, and on both datasets, it was computationally faster. These results reveal that simpler GRU structure is more adaptive, especially with stocks of high volatility like BBNI.
Comparative Analysis of LSTM and GRU Models for Predicting BBCA and BBNI Stock Prices Muhammad Irfansyah; Dendy K Pramudito; Sanudin
Jurnal Informatika Ekonomi Bisnis Vol. 8, No. 2 (June 2026)
Publisher : SAFE-Network

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/infeb.v8i2.1467

Abstract

Stock price predictions always a challenging issue as the price data consists of variable, noisy, non-linear time dependence. This research aims as a testing ground to compare the performance of two deep learning algorithms, long short-term memory and gated recurrent units, in predicting the end price of PT Bank Central Asia Tbk, that is relatively stable compares to PT Bank Negara Indonesia Tbk which more volatile. Daily prices were obtained from Yahoo Finance over the previous period from January1, 2019 until Dec 1, 2025. Data cleaning, Min-Max normalization, 80:20 data split, and sequence-formation with a timestep of 60 were performed. To facilitate fair comparison and ensure that the performance differences are only due to architecture, both models were constructed with the same architecture (two layers of 50 units, 0.2 dropout, Adam optimizer, MSE loss function, and 50 epochs). It evaluated MSE, RMSE performance, MAE performance, R-squared with accuracy adjusted for a 5% tolerance range. The results suggest that GRU outperforms LSTM on both stocks. For the BBCA, GRU reached an RMSE of 101.12, MAE of 113.82, R-squared of 0.96, and tolerance accuracy of 98.52%, compared to BBNI which had an RMSE of 62.95, MAE of 71.24, R-squared of 0.92, and tolerance accuracy of 94.11%. This performance led us to realize that GRU is the numerical equivalent to this technique, and on both datasets, it was computationally faster. These results reveal that simpler GRU structure is more adaptive, especially with stocks of high volatility like BBNI.
Co-Authors Dendy K Pramudito Muhammad Irfansyah