cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Auralia
Contact Email
submissions@ijarlit.org
Phone
-
Journal Mail Official
submissions@ijarlit.org
Editorial Address
Prenggan, Kotagede, Kota Yogyakarta, Daerah Istimewa Yogyakarta 55172, Indonesia
Location
Kota yogyakarta,
Daerah istimewa yogyakarta
INDONESIA
International Journal Artificial Intelligent and Informatics
Published by Research and Social Study Institute
ISSN : -     EISSN : 2622626X     DOI : https://doi.org/10.33292
Core Subject : Economy, Science,
Computer Science & IT Economics, Econometrics & Finance
International Journal of Artificial Intelligence and Informatics is a scientific journal dedicated to the exploration of theories, methods, and applications of artificial intelligence in time series analysis, forecasting, and prediction. This journal serves as a platform for researchers, academics, and practitioners to publish their work on predictive models applied to various time-dependent phenomena. Topics within the journal’s scope include, but are not limited to: 1. Predictive Methodologies and Models Deep learning models for forecasting (LSTM, GRU, Transformer, etc.) Machine learning algorithms for time series forecasting (ARIMA, SARIMA, XGBoost, etc.) Optimization of forecasting models using metaheuristic approaches (PSO, GA, etc.) Hybrid models for improving prediction accuracy Statistical methods and Bayesian approaches in forecasting 2. Applications of Time Series and Forecasting Across Various Fields Financial and stock market prediction Weather forecasting and climate change analysis Energy demand forecasting and resource management Time series analysis in healthcare and epidemiology Forecasting in manufacturing and supply chain management User behavior prediction in e-commerce and social media 3. Data and Infrastructure for Forecasting Big data management in time series analysis Streaming data and real-time forecasting Explainable AI (XAI) in predictive models Data augmentation and synthetic data for forecasting The journal welcomes research articles, review papers, and case studies that provide significant contributions to the development of theories and implementation of predictive systems based on artificial intelligence.
Arjuna Subject : Ilmu Komputer (semua kategori) - Kecerdasan Buatan
Articles 30 Documents
 1   2   3 
Comparison of LSTM and GRU Methods for Predicting Gold Exchange Rate against US Dollar Bohovic, Dušan
International Journal Artificial Intelligent and Informatics Vol 3, No 1 (2025)
Publisher : Research and Social Study Institute (ReSSI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (540.568 KB) | DOI: 10.33292/ijarlit.v3i1.43

Abstract

This study aims to compare the performance of Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models in predicting the gold exchange rate against the United States Dollar (USD). Using time series data from Yahoo Finance for the period 2017-2023, we evaluate and compare the two models based on comprehensive evaluation metrics. The results show that the GRU model performs better in several important metrics, especially in terms of Root Mean Square Error (RMSE) on the test data (26.41 compared to 27.54 on LSTM) and higher coefficient of determination (R²) on the test data (0.9004 compared to 0.7825 on LSTM). These findings indicate that the GRU model has better generalization ability for gold to USD exchange rate prediction, although both models show very high accuracy rates above 98% on the test data.
Petrobras Stock Price Prediction Using Deep Learning Approach: Performance Comparison of CNN and CNN-GRU Methods Gabrielzinho, Manuel; Moraes, Giovana
International Journal Artificial Intelligent and Informatics Vol 3, No 1 (2025)
Publisher : Research and Social Study Institute (ReSSI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (647.587 KB) | DOI: 10.33292/ijarlit.v3i1.44

Abstract

This study aims to compare the effectiveness of two deep learning models, namely Convolutional Neural Network (CNN) and combined CNN with Gated Recurrent Unit (CNN-GRU), in predicting Petrobras stock prices. Using historical stock price data from Yahoo Finance for the period 2017-2023, this study evaluates the performance of both models based on several evaluation metrics. The results showed that the CNN-GRU model outperformed the pure CNN model in all evaluation metrics, with an increase in RMSE value of 4.17% and an increase in R² value of 0.47% on the test data. The CNN-GRU model achieved 96.14% accuracy on the test data, while the CNN model achieved 96.04%. These findings indicate that the integration of CNN's feature extraction capabilities with GRU's temporal dependency modeling capabilities can improve stock price prediction accuracy. This research contributes to the computational finance literature by presenting an in-depth comparative analysis of the application of hybrid deep learning architectures in stock market prediction.
Prediction of Euro to US Dollar Exchange Rate Using CNN Method with Grid Optimization Al Anshori, Faqihuddin; Pidgeon, S
International Journal Artificial Intelligent and Informatics Vol 3, No 2 (2025)
Publisher : Research and Social Study Institute (ReSSI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (601.877 KB) | DOI: 10.33292/ijarlit.v3i2.45

Abstract

This research compares the performance of Convolutional Neural Network (CNN) models without optimization and CNN with Grid Search optimization in predicting the Euro exchange rate against the United States Dollar. Data obtained from Yahoo Finance for the period 2018-2023. The results showed that the CNN model with Grid Search optimization provided better performance with an RMSE value of 0.01, MAE of 0.01, MAPE of 0.61%, and R² of 0.8586 on test data, and prediction accuracy reached 99.39%. Grid Search optimization successfully found the best parameters with batch_size 32, dense_units 50, filters 64, kernel_size 3, and learning_rate 0.001. This research proves that hyperparameter optimization can improve the performance of CNN models in predicting currency exchange rates, which can be a decision support tool for foreign exchange market players.
Optimization of GRU Method with Bayesian Optimization for Prediction of South African Rand Exchange Rate against US Dollar Abdallah, Amme; Rahis, Saqib
International Journal Artificial Intelligent and Informatics Vol 3, No 2 (2025)
Publisher : Research and Social Study Institute (ReSSI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33292/ijarlit.v3i2.46

Abstract

This research compares the performance of the standard Gated Recurrent Unit (GRU) model with GRU optimized using Bayesian Optimization to predict the exchange rate of the South African Rand (ZAR) against the United States Dollar (USD). By utilizing time series data from Yahoo Finance for the period 2018-2023, this research implements a deep learning architecture to capture patterns of currency exchange rate fluctuations. The results show that the GRU model with Bayesian optimization produces better performance on the test data with a MAPE value of 0.81% and R² 0.9352, compared to the standard GRU model with a MAPE of 0.86% and R² 0.9267. Despite the slight decrease in accuracy on the training data, the optimized model has a simpler architecture with a single GRU layer, which indicates better computational efficiency. These findings make a significant contribution to the development of more accurate and efficient currency exchange rate prediction models, particularly for emerging financial markets.
Comparison of LSTM and LSTM with Grid Search Optimization for Stock Price Prediction of Saudi Arabian Oil Company (Aramco) Yilmaz, Eva; Tcrol, Ema
International Journal Artificial Intelligent and Informatics Vol 3, No 2 (2025)
Publisher : Research and Social Study Institute (ReSSI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (407.514 KB) | DOI: 10.33292/ijarlit.v3i2.47

Abstract

This study compares the performance of the Long Short-Term Memory (LSTM) model without optimization and LSTM with Grid Search optimization in predicting Saudi Arabian Oil Company (Aramco) stock prices. Using stock price data from December 2019 to December 2023, this study aims to identify a more accurate prediction model. Results show that the LSTM model with Grid Search optimization provides a significant performance improvement compared to the standard LSTM model, with a decrease in Root Mean Square Error (RMSE) of 11.63% on the test data. This finding indicates the importance of hyperparameter optimization in improving the accuracy of stock price prediction models, especially for the world's largest oil company such as Aramco, whose stock price can be affected by various macroeconomic and geopolitical factors.
Performance Comparison of Standard LSTM and LSTM with Random Search Optimization for Spark New Zealand Limited Stock Price Prediction Flavia, Axia; Mio, Camila
International Journal Artificial Intelligent and Informatics Vol 3, No 2 (2025)
Publisher : Research and Social Study Institute (ReSSI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (708.211 KB) | DOI: 10.33292/ijarlit.v3i2.48

Abstract

This study compares the performance of the standard Long Short-Term Memory (LSTM) model with the LSTM model optimized using the Random Search method to predict the stock price of Spark New Zealand Limited. The data used is historical stock price data from Yahoo Finance for the period 2018-2023. Model evaluation is performed using Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), coefficient of determination (R²), and accuracy metrics. The results showed that the standard LSTM model achieved Test RMSE performance of 0.04, Test MAE of 0.03, Test MAPE of 0.73%, Test R² of 0.8571, and Test Accuracy of 99.27%. While the LSTM model with Random Search optimization achieved Test RMSE performance of 0.04, Test MAE of 0.03, Test MAPE of 0.78%, Test R² of 0.8302, and Test Accuracy of 99.22%. Although both models performed very well, the standard LSTM model was slightly superior in some evaluation metrics on the test data. This research provides insight into the effectiveness of hyperparameter optimization in the context of stock price prediction.
Comparison of CNN, CNN-GRU, and GRU Models for Prediction of Hryvnia (Ukraine) Exchange Rate against US Dollar Mostafa, Sanoun
International Journal Artificial Intelligent and Informatics Vol 3, No 2 (2025)
Publisher : Research and Social Study Institute (ReSSI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (353.381 KB) | DOI: 10.33292/ijarlit.v3i2.49

Abstract

This study aims to compare the performance of three neural network-based machine learning models, namely Convolutional Neural Network (CNN), hybrid CNN-Gated Recurrent Unit (CNN-GRU), and Gated Recurrent Unit (GRU) in predicting the exchange rate of the Ukrainian Hryvnia against the United States Dollar. The data used is sourced from Yahoo Finance in the range of 2018 to 2023. The evaluation results show that the CNN-GRU hybrid model provides the best performance with the highest test accuracy of 99.69% and an R² value of 0.6899. The CNN model achieved 98.99% test accuracy but with a negative R² (-1.0343), while the GRU model showed 97.94% test accuracy with a very low R² (-6.3755). This study reveals the advantages of the hybridization approach in modeling financial time series data by combining the feature extraction capabilities of CNN and the sequential modeling capabilities of GRU. These results provide important insights for the development of predictive models for volatile currency markets, especially for emerging economies such as Ukraine.
Stock Price Prediction of ReconAfrica (RECAF) Using Gated Recurrent Unit (GRU): Analysis and Implications for Investment Decisions Aníbal, Tomás López; Okanlawon, Rabiu
International Journal Artificial Intelligent and Informatics Vol 2, No 2 (2024)
Publisher : Research and Social Study Institute (ReSSI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33292/ijarlit.v2i2.35

Abstract

This study develops a stock price prediction model for ReconAfrica (RECAF) using Gated Recurrent Unit (GRU), an effective deep learning method for capturing temporal and non-linear patterns in stock price data. The model was trained and tested using five years of historical RECAF stock price data and evaluated with metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and Mean Absolute Percentage Error (MAPE). The evaluation results show that the GRU model achieved an MAE of 0.0992, MSE of 0.0397, RMSE of 0.1993, and MAPE of 4.27, indicating a high predictive capability. These findings underscore the potential of the GRU model as a valuable tool for investors and market analysts in making more informed investment decisions. While the results are promising, the study also identifies opportunities for further development through the integration of external data and exploration of other deep learning architectures. Thus, this research contributes significantly to stock market analysis and improved investment strategies.
Improved Accuracy of Ethereum Exchange Rate Prediction Against USD Using CNN-LSTM Hybrid Model with Bayesian Optimization Tamene, Panom; Chernet, Ghugza
International Journal Artificial Intelligent and Informatics Vol 3, No 1 (2025)
Publisher : Research and Social Study Institute (ReSSI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33292/ijarlit.v3i1.40

Abstract

This study evaluates the effectiveness of the CNN-LSTM hybrid model in predicting the Ethereum exchange rate against the United States Dollar (USD) by comparing the performance of the model without optimization and the model with hyperparameter optimization using Bayesian Optimization. The dataset used is sourced from Yahoo Finance covering the period 2017-2023. The results show that the CNN-LSTM model with hyperparameter optimization consistently outperforms the model without optimization, with improved prediction accuracy shown through the RMSE, MAE, MAPE, and R² values. Hyperparameter optimization resulted in an optimal configuration with 166 filters, kernel size 5, 168 LSTM units, 91 dense units, learning rate 0.00114, and batch size 32. This research confirms the effectiveness of the CNN-LSTM hybrid approach in predicting crypto exchange rates, and demonstrates the importance of hyperparameter optimization in improving prediction accuracy.
Forecasting Stock Prices of Taiwan Semiconductor Manufacturing Company (TSMC) Using Recurrent Neural Networks: Evaluating Predictive Performance in a Volatile Market li-We, Lai; Moanu, Koundé
International Journal Artificial Intelligent and Informatics Vol 2, No 2 (2024)
Publisher : Research and Social Study Institute (ReSSI)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33292/ijarlit.v2i2.38

Abstract

Accurate stock price prediction plays a critical role in guiding investment strategies, particularly in dynamic industries such as semiconductors, where price volatility is high. This study investigates the effectiveness of Recurrent Neural Networks (RNN) in predicting the stock prices of Taiwan Semiconductor Manufacturing Company (TSMC), a global leader in the semiconductor sector. Using daily closing price data from January 2020 to January 2023, the RNN model was developed and trained to forecast future stock prices. The data was preprocessed with feature scaling to ensure the stability of model training, and a sliding window approach was applied to capture temporal dependencies. The model's predictive performance was evaluated using Root Mean Squared Error (RMSE) and Mean Absolute Percentage Error (MAPE) as key metrics. The RNN achieved an RMSE of 9.87 and a MAPE of 5.90%, indicating that the model provides reasonable accuracy in forecasting stock prices with a moderate level of deviation from actual values. Visual analysis further demonstrated the model's capacity to capture general trends in the stock price movements, although challenges were noted in predicting highly volatile periods. The study highlights the potential of RNN in financial forecasting while suggesting future improvements, such as incorporating advanced models like Long Short-Term Memory (LSTM) or external factors to enhance predictions during market volatility. These findings offer valuable insights for investors and analysts seeking to leverage machine learning in stock price prediction, particularly in industries characterized by rapid technological advancements and price fluctuations.

Page 3 of 3 | Total Record : 30

 1   2   3 

Filter by Year

2018 2025


Reset
Filter By Issues
All Issue Vol 3, No 2 (2025) Vol 3, No 1 (2025) Vol 2, No 2 (2024) Vol 2, No 1 (2024) Vol 1, No 2 (2018) Vol 1, No 1 (2018)