Research Article
BibTex RIS Cite

Comparative Analysis of LSTM and ARIMA Models in Stock Price Prediction: A Technology Company Example

Year 2024, Volume: 7 Issue: 5, 15 - 16
https://doi.org/10.34248/bsengineering.1445997

Abstract

Hisse senedi fiyat tahmini, ekonomistler ve bilgisayar bilimcileri için önemli bir ilgi alanı olmuştur. Geleneksel istatistiksel yöntemlerin yanı sıra, makine öğrenimi gibi gelişmiş yapay zeka teknikleri, karmaşık veri setlerini işleme ve geçmiş verilere uyum sağlama yetenekleriyle öne çıkabilmektedir. Son yıllarda, derin öğrenme ve zaman serisi yöntemlerini birleştiren hibrit modeller, hisse senedi seçimi ve portföy optimizasyonunda üstün performans göstermiştir. Bu çalışma, LSTM ve ARIMA modellerinin zaman serisi tahminindeki performansını karşılaştırmalı olarak analiz etmektedir. Çalışmada, Oracle şirketinin hisse senedi fiyatları LSTM ve ARIMA olmak üzere iki farklı model kullanılarak tahmin edilmiştir. Model performansı MSE, MAE, RMSE ve MAPE gibi metrikler kullanılarak değerlendirilmiştir. Her iki model de farklı metriklerde başarılı bulunmuştur. LSTM modeli daha düşük hata değerlerine sahiptir; ARIMA modeli ise oransal olarak daha doğru tahminler üretmiştir. Çalışma, derin öğrenmenin sunduğu potansiyel göz önüne alındığında, LSTM gibi modellerin zaman serisi tahmini için gerekli olduğu sonucuna varmaktadır. Derin öğrenmenin esnekliği, farklı veri türleri ve zaman serisi problemleri için özelleştirilmiş modellerin geliştirilmesine olanak sağlamaktadır.

References

  • Agrawal JG, Chourasia V, Mittra A. 2013. State-of-the-art in stock prediction techniques. Int J Adv Res Electr Electron Instrum Eng, 2(4): 1360-1366.
  • Bustos O, Quimbaya A. 2020. Stock market movement forecast: A systematic review. Expert Syst Appl, 156: 113464. Choi J, Yoo S, Zhou X, Kim Y. 2023. Hybrid information mixing module for stock movement prediction. IEEE Access, 11: 28781-28790.

Comparative Analysis of LSTM and ARIMA Models in Stock Price Prediction: A Technology Company Example

Year 2024, Volume: 7 Issue: 5, 15 - 16
https://doi.org/10.34248/bsengineering.1445997

Abstract

Stock price forecasting has been an important area of interest for economists and computer scientists. In addition to traditional statistical methods, advanced artificial intelligence techniques such as machine learning can stand out with their ability to process complex data sets and adapt to historical data. In recent years, hybrid models combining deep learning and time series methods have demonstrated superior performance in stock selection and portfolio optimisation. This study comparatively analyses the performance of LSTM and ARIMA models in time series forecasting. In the study, the stock prices of Oracle company are predicted using two different models, LSTM and ARIMA. Model performance is evaluated using metrics like MSE, MAE, RMSE, and MAPE. Both models have been found to be successful in different metrics. The LSTM model has lower error values; meanwhile, the ARIMA model produced proportionally more accurate forecasts. The study concludes that given the potential offered by deep learning, models such as LSTM are essential for time series forecasting. The flexibility of deep learning allows the development of customized models for different data types and time series problems.

References

  • Agrawal JG, Chourasia V, Mittra A. 2013. State-of-the-art in stock prediction techniques. Int J Adv Res Electr Electron Instrum Eng, 2(4): 1360-1366.
  • Bustos O, Quimbaya A. 2020. Stock market movement forecast: A systematic review. Expert Syst Appl, 156: 113464. Choi J, Yoo S, Zhou X, Kim Y. 2023. Hybrid information mixing module for stock movement prediction. IEEE Access, 11: 28781-28790.
There are 2 citations in total.

Details

Primary Language English
Subjects Information Systems Development Methodologies and Practice, Information Systems (Other), Multiple Criteria Decision Making
Journal Section Research Articles
Authors

Yasin Kırelli 0000-0002-3605-8621

Early Pub Date August 12, 2024
Publication Date
Submission Date March 1, 2024
Acceptance Date July 30, 2024
Published in Issue Year 2024 Volume: 7 Issue: 5

Cite

APA Kırelli, Y. (2024). Comparative Analysis of LSTM and ARIMA Models in Stock Price Prediction: A Technology Company Example. Black Sea Journal of Engineering and Science, 7(5), 15-16. https://doi.org/10.34248/bsengineering.1445997
AMA Kırelli Y. Comparative Analysis of LSTM and ARIMA Models in Stock Price Prediction: A Technology Company Example. BSJ Eng. Sci. August 2024;7(5):15-16. doi:10.34248/bsengineering.1445997
Chicago Kırelli, Yasin. “Comparative Analysis of LSTM and ARIMA Models in Stock Price Prediction: A Technology Company Example”. Black Sea Journal of Engineering and Science 7, no. 5 (August 2024): 15-16. https://doi.org/10.34248/bsengineering.1445997.
EndNote Kırelli Y (August 1, 2024) Comparative Analysis of LSTM and ARIMA Models in Stock Price Prediction: A Technology Company Example. Black Sea Journal of Engineering and Science 7 5 15–16.
IEEE Y. Kırelli, “Comparative Analysis of LSTM and ARIMA Models in Stock Price Prediction: A Technology Company Example”, BSJ Eng. Sci., vol. 7, no. 5, pp. 15–16, 2024, doi: 10.34248/bsengineering.1445997.
ISNAD Kırelli, Yasin. “Comparative Analysis of LSTM and ARIMA Models in Stock Price Prediction: A Technology Company Example”. Black Sea Journal of Engineering and Science 7/5 (August 2024), 15-16. https://doi.org/10.34248/bsengineering.1445997.
JAMA Kırelli Y. Comparative Analysis of LSTM and ARIMA Models in Stock Price Prediction: A Technology Company Example. BSJ Eng. Sci. 2024;7:15–16.
MLA Kırelli, Yasin. “Comparative Analysis of LSTM and ARIMA Models in Stock Price Prediction: A Technology Company Example”. Black Sea Journal of Engineering and Science, vol. 7, no. 5, 2024, pp. 15-16, doi:10.34248/bsengineering.1445997.
Vancouver Kırelli Y. Comparative Analysis of LSTM and ARIMA Models in Stock Price Prediction: A Technology Company Example. BSJ Eng. Sci. 2024;7(5):15-6.

                                                24890