Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal RABIT: Jurnal Teknologi dan Sistem Informasi Univrab
Fatia Naura
Universitas Malikussaleh
Computer Science & IT Engineering

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
PERBANDINGAN PREDIKSI HARGA SAHAM DENGAN MENGGUNAKAN METODE RECURRENT NEURAL NETWORK DAN LONG SHORT TERM MEMORY Fatia Naura; Safwandi; Rizki Suwanda
Rabit : Jurnal Teknologi dan Sistem Informasi Univrab Vol 11 No 2 (2026): Juli
Publisher : LPPM Universitas Abdurrab

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36341/rabit.v11i2.8345

Abstract

Unpredictable stock price fluctuations encourage the use of artificial intelligence methods based on deep learning. This study compares the performance of Recurrent Neural Network (RNN) and Long Short-Term Memory (LSTM) in predicting the share price of PT Pacific Strategic Financial Tbk. using 346 daily historical data (January 2024–June 2025) sourced from Investing.com. The data collected includes daily stock prices, such as opens, closes, highs, lows, and trading volumes, which will be used to train and test the prediction model. The research stages include pre-processing of data (Min-Max normalization and windowing), model design and training, evaluation using Mean Squared Error (MSE) and Mean Absolute Error (MAE), 5-fold cross-validation, and window size sensitivity analysis. The results showed that RNN was slightly superior to LSTM in prediction accuracy (MSE 0.001417 vs 0.001514; MAE 0.030937 vs 0.031938), inter-fold consistency, and computational efficiency of RNN parameters is only a quarter and memory usage is 1.5 times more efficient than LSTM. In contrast, LSTMs produce predictive patterns that are more visually refined and potentially more suitable for long-term trend analysis. The limited number of data (346 observations) on one issuer is allegedly a factor that limits the theoretical advantages of LSTM gating architecture. These findings imply that RNNs are a more efficient option for short-term stock price predictions with limited data, while LSTMs are more relevant for long-term trend analysis needs on larger volumes of data.  
Co-Authors Rizki Suwanda Safwandi Safwandi