Home About Login Current Archives Announcements Editorial Board
Submit Now For Authors Call for Submissions Statistics Contact
Home > Archives > Volume 20, No 7 (2022) > Article

DOI: 10.14704/nq.2022.20.7.NQ33472

Stock Price Prediction based on Generative Adversarial Network

M. Dhivya, Dr.V.Maniraj


The prediction of stock market system provides a framework for businesses to maximize profits in the stock market. The increase in the huge amounts of information relating to the financial markets makes it challenging to effectively evaluate and forecast the stock market. Data from the stock market is time-series data in which the value of stock varies over time. Accurate stock market analysis prediction remains a difficult task. The advancement of deep learning (DL) techniques has attracted interest in forecasting future stock market trends. This paper proposes the Generative Adversarial Network (GAN) as a forecasting methodology for stock market forecasting. The GAN contains a generator and discriminator. LSTM is used in the generator, and CNN is used in the discriminator. Also, CNN is utilized in the extraction of features from the stock market dataset. The suggested system's performance is assessed with MAE, MSE, RMSE, MAPE and R2.


LSTM, CNN, Deep Learning, Generative Adversarial Network (GAN)

Full Text