Academic Journal of Computing & Information Science, 2023, 6(7); doi: 10.25236/AJCIS.2023.060715.
Zijie Zhong1, Difei Wu1, Wenxuan Mai2
1School of Data Science, Beijing Normal University - Hong Kong Baptist University United International College, Zhuhai, 519087, China
2School of Data Science, Beijing Normal University - Hong Kong Baptist University United International College, Zhuhai, 519087, China
Although the market is getting back into order after COVID-19, it is still continuously affected by the epidemic virus. Researchers try to understand how a piece of stock changes over a period of time before and after COVID-19, in order to provide reliable marketing decisions to society. In this paper, using ARIMA (Auto-regressive Integrated Moving Average) model and GRU (Gate Recurrent Unit) model, we analyse close price of Apple stock from 2018 to 2023 (1258 data in total) and use 70% of data for model training, whereas the remaining 30% of data are for model prediction and evaluation. Results show that the ARIMA model is able to extract trend of the stock but has bad performance on fitting and predicting real data; the R-square for GRU on test data reaches to 0.936.
Stock Prediction, ARIMA model, GRU model
Zijie Zhong, Difei Wu, Wenxuan Mai. Stock Prediction Based on ARIMA Model and GRU Model. Academic Journal of Computing & Information Science (2023), Vol. 6, Issue 7: 114-123. https://doi.org/10.25236/AJCIS.2023.060715.
[1] C.I. Noshi, A.I. Assem, J. J. Schubert. The role of big data analytics in exploration and production: a review of benefits and applications. SPE International Heavy Oil Conference and Exhibition, Society of Petroleum Engineers (2018).
[2] J. Brownlee. White Noise Time Series with Python (2017). Retrieved from White Noise Time Series with Python - MachineLearningMastery.com.
[3] PennState. Retrieved from https://online.stat.psu.edu/stat510/lesson/2/2.2 (2014).
[4] Yanrui Ning, Hossein Kazemi, Pejman Tahmasebi. A comparative machine learning study for time series oil production forecasting: ARIMA, LSTM, and Prophet. Computers & Geosciences, Volume 164, July 2022, 105126.
[5] L. Jain, L. Medsker. Recurrent Neural Networks: Design and Applications. International Series on Computational Intelligence. CRC-Press (1999).