Welcome to Francis Academic Press

Academic Journal of Business & Management, 2023, 5(10); doi: 10.25236/AJBM.2023.051011.

Predicting TSLA Stock Price Based on LSTM and GRU Models

Author(s)

Yishan Zhang, Yuge Cui

Corresponding Author:
Yishan Zhang
Affiliation(s)

Actuarial Science, Xi’an Jiaotong-Liverpool University, Renai Roud, Suzhou, China

Abstract

In recent years, advancements in artificial intelligence technologies have facilitated their successful application in time series forecasting and analytical tasks. With the objective of fostering growth in the stock market, this study employs two well-established deep learning forecasting models, namely Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), to predict TESLA stock prices. Initially, historical data is utilized to project future stock prices, and a comparative analysis of the two models is conducted, concluding that a hybrid LSTM+GRU model demonstrates superior performance compared to a standalone LSTM model when provided with identical data. Furthermore, to enhance prediction accuracy, time series data is smoothed using either moving average or exponential average techniques, resulting in a significant improvement in the performance of the LSTM model as compared to both its previous performance and the LSTM+GRU model.

Keywords

Tesla, Green Stock, Stock Market, LSTM, GRU

Cite This Paper

Yishan Zhang, Yuge Cui. Predicting TSLA Stock Price Based on LSTM and GRU Models. Academic Journal of Business & Management (2023) Vol. 5, Issue 10: 72-77. https://doi.org/10.25236/AJBM.2023.051011.

References

[1] Bhadamkar A. and Bhattacharya, S. (2022) ‘Tesla Inc. Stock Prediction using Sentiment Analysis’, Australasian Accounting Business & Finance Journal, 16(5), pp. 52–66. doi:10.14453/aabfj.v16i5.05 (Accessed: 22 April 2023).

[2] Alkhatib K. et al. (2022) ‘A New Stock Price Forecasting Method Using Active Deep Learning Approach’, Journal of Open Innovation, 8(2), p. 96. doi:10.3390/joitmc8020096 (Accessed: 22 April 2023).

[3] Ratchagit M. and Xu H. (2022) ‘A Two-Delay Combination Model for Stock Price Prediction’, Mathematics (2227-7390), 10(19), p. 3447. doi:10.3390/math10193447 (Accessed: 22 April 2023).

[4] Albahli S. et al. (2022) ‘A Machine Learning Method for Prediction of Stock Market Using Real-Time Twitter Data’, Electronics (2079-9292), 11(20), p. 3414–N.PAG. doi: 10.3390/ electronics 11203414 (Accessed: 22 April 2023).

[5] Lv J. et al. (2021) ‘An Economic Forecasting Method Based on the LightGBM-Optimized LSTM and Time-Series Model’, Computational Intelligence & Neuroscience, pp. 1–10. doi:10.1155/2021/8128879 (Accessed: 22 April 2023).

[6] Wang J. et al. (2022) ‘Predicting Stock Market Volatility from Candlestick Charts: A Multiple Attention Mechanism Graph Neural Network Approach’, Mathematical Problems in Engineering, pp. 1–16. doi:10.1155/2022/4743643 (Accessed: 22 April 2023).

[7] Ho T.-T., Huang Y. (2021) ‘Stock Price Movement Prediction Using Sentiment Analysis and CandleStick Chart Representation’, Sensors (14248220), 21(23), p. 7957. doi:10.3390/s21237957 (Accessed: 22 April 2023).

[8] Kamal S. et al. (2022) ‘Trading Stocks Based on Financial News Using Attention Mechanism’, Mathematics (2227-7390), 10(12), p. 2001–N.PAG. doi:10.3390/math10122001 (Accessed: 22 April 2023).

[9] Hochreiter S. and Schmidhuber J. (1997) ‘Long short-term memory’, Neural Computation, 9(8), p. 1735. doi:10.1162/neco.1997.9.8.1735 (Accessed: 22 April 2023).

[10] Graves A. (2012) Supervised Sequence Labelling with Recurrent Neural Networks. [electronic resource]. 1st ed. 2012. Springer Berlin Heidelberg (Studies in Computational Intelligence: 385). Available at: https://search-ebscohost-com.ez. xjtlu.edu.cn/l ogin.aspx? direct= true&db= cat01010a&AN= xjtlu.0001536424&site=eds-live&scope=site (Accessed: 22 April 2023).

[11] Cho K. et al. (2014) ‘Learning Phrase Representations using RNN Encoder-Decoder for Statistical Machine Translation’. Available at: https:// search-ebscohost-com. ez.xjtlu.edu.cn/login.aspx? direct=true&db=edsarx&AN=edsarx. 1406.1078&site=eds-live&scope=site (Accessed: 22 April 2023).