Author(s)

Zhiming Zhou ¹, Zhensheng Huang ¹

Affiliation(s)

¹ School of Mathematics and Statistics, Nanjing University of Science & Technology, Nanjing, 210094, China

Corresponding Author

Zhensheng Huang

ABSTRACT

Studying stock market prediction and coming up with an effective forecasting model can help investors reduce investment risk. But it’s more difficult to predict Chinese stock market (A-share) than that of developed countries because of its unique characteristics. This paper tried to make some progress on this problem and has acquired notable results. In this paper, we construct a generative adversarial network with shared pre-learning network (SPN-GAN) by introducing a pre-learning network into the architecture of GAN which is shared by generator (G) and discriminator (D) and adding a directional sub-discriminator into D out of consideration of forecasting accuracy of moving direction. SPN can preliminarily extract hidden representation from original indicators and the design of shared structure significantly reduced model complexity and training cost. The performance of proposed model is evaluated using 4 representative A-share stock indices. Results show that SPN-GAN outperforms traditional machine learning models and deep learning models in most cases.

KEYWORDS

Stock index prediction, deep learning, GAN, feature selection

CITE THIS PAPER

Zhiming Zhou, Zhensheng Huang, Research on Forecasting A-share Stock Index Using a Modified Generative Adversarial Network. Financial Engineering and Risk Management (2023) Vol. 6: 88-100. DOI: http://dx.doi.org/10.23977/ferm.2023.060412.

REFERENCES

[1] Sharaf M., Hemdan E.E., El-Sayed A. and El-Bahnasawy N.A. (2021) StockPred: a framework for stock Price prediction. Multimedia Tools And Applications, 12, 17923-17954.
[2] Qiu Y., Song Z.W. and Chen Z.S. (2022) Short-term stock trends prediction based on sentiment analysis and machine learning. Soft Computing, 5, 2209-2224.
[3] Goodfellow I., Bengio Y. and Courville A. Deep learning. MIT Press, Cambridge, MA, 2016.
[4] Jiang W. (2021) Applications of deep learning in stock market prediction: Recent progress. Expert Systems with Applications, 184.
[5] Zaheer S., Anjum N., Hussain S., Algarni A.D., Iqbal J., Bourouis S. and Ullah S.S. (2023) A Multi Parameter Forecasting for Stock Time Series Data Using LSTM and Deep Learning Model. Mathematics, 3.
[6] Goodfellow I.J., Pouget-Abadie J., Mirza M., Xu B., Warde-Farley D., Ozair S., Courville A. and Bengio Y. (2014) Generative Adversarial Nets. Proceedings of Advances In Neural Information Processing Systems, 2672-2680.
[7] He B. and Kita E. (2020) Stock Price Prediction by Using Hybrid Sequential Generative Adversarial Networks. proceedings of the 20th IEEE International Conference on Data Mining (ICDM).
[8] Wu W., Huang F., Kao Y., Chen Z. and Wu Q. (2021) Prediction Method of Multiple Related Time Series Based on Generative Adversarial Networks. Information, 2.
[9] Vaswani A., Shazeer N., Parmar N., Uszkoreit J., Jones L., Gomez A.N., Kaiser Ł. and Polosukhin I. (2017) Attention is all you need. Advances in neural information processing systems.
[10] Kingma D.P. and Ba J. (2014) Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980.
[11] Yun K.K., Yoon S.W. and Won D. (2021) Prediction of stock price direction using a hybrid GA-XGBoost algorithm with a three-stage feature engineering process. Expert Systems with Applications, 115716.
[12] Benediktsson J. Python wrapper for TA-Lib. https://ta-lib.github.io/ta-lib-python.
[13] Lin Y.H., Liu S.C., Yang H. and Wu H. (2021) Stock Trend Prediction Using Candlestick Charting and Ensemble Machine Learning Techniques With a Novelty Feature Engineering Scheme. IEEE ACCESS, 101433-101446. 

Sponsors, Associates, and Links

---

• Information Systems and Economics
  
  
• Accounting, Auditing and Finance
  
  
• Industrial Engineering and Innovation Management
  
  
• Tourism Management and Technology Economy
  
  
• Journal of Computational and Financial Econometrics
  
  
• Accounting and Corporate Management
  
  
• Social Security and Administration Management
  
  
• Population, Resources & Environmental Economics
  
  
• Statistics & Quantitative Economics
  
  
• Agricultural & Forestry Economics and Management
  
  
• Social Medicine and Health Management
  
  
• Land Resource Management
  
  
• Information, Library and Archival Science
  
  
• Journal of Human Resource Development
  
  
• Manufacturing and Service Operations Management
  
  
• Operational Research and Cybernetics