PERFORMANCE ANALYSIS OF RECURRENT NEURAL NETWORK MODEL WITH PRE-COVID AND POST-COVID STOCK MARKET DATASET

International Journal of Computer Science (IJCS) Published by SK Research Group of Companies (SKRGC)

Abstract

The results of a neural network model depend on the selection of parameters. The parameters may include the quantity of the dataset, type of architecture, learning algorithm, data division ratio, etc. The idea of this research study is to find the optimal parameters of the Recurrent Neural Network (RNN) model for the prediction of the Bombay Stock Exchange market and analyze the performance of the RNN model by using a different range of datasets. The dataset range is classified as stock market index data during the COVID period, post-covid period, pre-covid period and the entire period, which includes pre-covid, post-covid and during the covid period. 150 candidate models were generated for every dataset; a total of 600 candidate models were generated, and the best models were selected for every dataset. The results of the RNN model perform well even though there is a fluctuation in stock market data.

References

1. WHO "Online" https://www.who.int/news-room/q-a-detail/q-a-coronaviruses (Accessed on September-28, 2022)

2. D. Ashok kumar and S. Murugan, “'Performance Analysis of Indian Stock Market Index using Neural Network Time series Models”, IEEE Explore Digital Library, pp.72-78, 2013.

3. D. Ashok kumar and S. Murugan, “'Performance Analysis of MLPFF Neural Network Back propagation Training Algorithms for Time Series Data'”, IEEE Explore Digital Library, pp.114-119, 2014.

4. D. Ashok kumar and S. Murugan, “Performance Analysis of Different Data Division Ratio for Time Series Data Using Multi Layer Feed Forward Neural Network with Tracking Signal Approach”, , International Journal of Control Theory and Applications, Vol 10, Number 11, 2017.

5. D. Ashok kumar and S. Murugan, “A Novel Fuzzy Time Series Model for Stock Market Index Analysis using Neural Network with Tracking Signal Approach”, Indian Journal of Science and Technology Vol 10 (16), April 2017.

6. D. Ashok kumar and S. Murugan, “Performance Analysis of NARX Neural Network Back Propagation Algorithm by Various Training Functions for Time Series Data”, International Journal of Data Science, Vol 3 (4), November 2018.

7. Greg Heath, “Problem about getting optimum output in Neural Network MATLAB 2012a”, http://in.mathworks.com/matlab central/ newsreader/view thread/331714

8. Jeff Heaton , “Introduction to Neural Networks for Java”, Heaton Research, Inc, Second Edition, pp. 159-160, 2008.

9. A. Adebiyi Ayodele, K. Ayo Charles, O. Adebiyi Marion and O. Otokiti Sunday, “Stock Price Prediction using Neural Network with Hybridized Market Indicators”, Journal of Emerging Trends in Computing and Information Sciences, Vol. 3, pp. 1-9, 2012.

10. Ricardo de A.Araujo, and Tiago A.E. Ferreira, “An intelligent hybrid morphological-rank-linear method for financial time series prediction”, Neurocomputing, Vol. 72, pp. 2507-2524, 2009.

11. T. Victor Devadoss, and T. Antony Alphonnse Ligori, “Stock Prediction Using Artificial Neural Networks”, International Journal of Data Mining Techniques and Applications, Vol. 2, pp. 283-291, 2013.

12. T. Victor Devadoss, and T. Antony Alphonnse Ligori, “Forecasting of Stock Prices Using Multi Layer Perceptron”, International Journal of Computing Algorithm, Vol. 2, pp. 440-449, 2013.

13. Zhang Yudong, and Wu Lenan, “'Stock market prediction of S&P 500 via combination of improved BCO approach and BP neural network”, Expert Systems with Applications, Vol. 36, pp. 8849-8854, 2009.

14. R. Adhikari, and R. K. Agrawal, “An introductory study on time series modeling and forecasting”, LAP Lambert Academic Publishing, Germany, pp. 1-67, 2007.

15. K. K. Suresh Kumar, “Performance analysis of stock price prediction using artificial neural network”, Global Journal of Computer Science and Technology, pp. 154-170, 2012.

16. Derrick T. Mirikitani, and Nikolay Nikolaev, “Recursive Bayesian Recurrent Neural Networks for Time-Series Modeling”, IEEE TRANSACTIONS ON NEURAL NETWORKS, VOL. 21, NO. 2, FEBRUARY 2010.

Keywords

Recurrent Neural Network, Covid, Bombay Stock Market, Performance Analysis, Time Series Data.