cover
Contact Name
Antomi Saregar
Contact Email
antomisaregar@radenintan.ac.id
Phone
+6285279618867
Journal Mail Official
antomisaregar@radenintan.ac.id
Editorial Address
Jl. Letnan Kolonel H Endro Suratmin, Sukarame, Kec. Sukarame, Kota Bandar Lampung, Lampung
Location
Kota bandar lampung,
Lampung
INDONESIA
International Journal of Electronics and Communications Systems
ISSN : -     EISSN : 27982610     DOI : 10.24042
International Journal of Electronics and Communications System (IJECS) [e-ISSN: 2798-2610] is a medium communication for researchers, academicians, and practitioners from all over the world that covers issues such as the improvement about design and implementation of electronics devices, circuits, and communication systems including but not limited to: circuit theory, integrated circuits, analog circuits, digital circuits, mixed-signal circuits, electronic components, filters, oscillators, biomedical circuits, neuromorphic circuits, RF circuits, optical communication systems, microwave systems, antenna systems, communications circuits for optical communication, development of physics evaluation instruments, development of physics instructional media, digital signal processing, communication theory and techniques, modulation, source and channel coding, microwave theory and techniques, wave propagation and more.
Articles 61 Documents
Hybrid CNN–LSTM–Transformer Architectures for Stock Price Prediction: Comparing Sequential and Parallel Integration Strategies Taufik, Mhd; Zahra, Amalia
International Journal of Electronics and Communications Systems Vol. 6 No. 1 (2026): International Journal of Electronics and Communications System
Publisher : Universitas Islam Negeri Raden Intan Lampung, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24042/ijecs.v6i1.29617

Abstract

Accurate stock price forecasting remains challenging because financial time-series exhibit complex local patterns, long-term temporal dependencies, and rapidly changing market dynamics. Although hybrid deep learning models have demonstrated promising predictive capabilities, limited evidence is available on how different architectural integration strategies influence forecasting performance. This study compares sequential and parallel hybrid CNN–LSTM–Transformer architectures enhanced with attention mechanisms and Bayesian optimization for predicting BBNI stock prices. Historical market data were processed through convolutional, recurrent, and attention-based learning components, while Bayesian optimization was employed to identify optimal hyperparameter configurations. Both hybrid architectures consistently outperformed the baseline CNN–LSTM model, demonstrating substantial improvements in prediction accuracy. The parallel architecture achieved superior performance in minimizing large prediction errors and explaining variance, whereas the sequential architecture produced lower absolute prediction errors with greater computational efficiency. These findings indicate that predictive performance depends not only on model complexity but also on the way deep learning components are structurally integrated. The study provides practical guidance for designing hybrid forecasting architectures that balance predictive accuracy and computational efficiency for financial time-series prediction in emerging markets.