Optimal neural network architecture for stock market forecasting

Gitansh Khirbat, Rahul Gupta, Sanjay Singh

Research output: Contribution to conferencePaper

7 Citations (Scopus)

Abstract

Predicting stocks accurately has always intrigued the market analysts. A possible forecast of stocks is done using trading parameters and Price/Earnings ratio. With the advances in Artificial Neural Networks, it has become possible to analyze a data set in temporal domain. The use of Time Series Forecasting empowers us to predict the value of an entity in the future based on the previously obtained outputs. The current best fit solution for stock forecasting produces a forecast result with 58% accuracy using feed-forward backpropagation neural network. In this paper, we have represented the data set containing financial stock price as a time series. This time series is forecasted by feeding it to a multi layer back propagation neural network. In real world scenario, stock prices are influenced by many non\ deterministic factors such as national & international economy and public confidence. This paper takes into account factors like Earnings Per Share (EPS) and public confidence and introduces an empirically defined neural network architecture of the form [m - m/2 - m/10 - 1] which gives an optimized structure for predicting the future value of a stock by extrapolating the near future value by the present value comparisons. The experimental results obtained after the training and testing of the financial data are very promising. This increase in accuracy of our financial prediction is due to the factors incorporated for forecasting which can give a clear binary classification for buying or withholding the stock in the current market scenario.

Original languageEnglish
Pages557-561
Number of pages5
DOIs
Publication statusPublished - 05-08-2013
Event3rd International Conference on Communication Systems and Network Technologies, CSNT 2013 - Gwalior, India
Duration: 06-04-201308-04-2013

Conference

Conference3rd International Conference on Communication Systems and Network Technologies, CSNT 2013
CountryIndia
CityGwalior
Period06-04-1308-04-13

Fingerprint

Network architecture
Neural networks
Time series
Backpropagation
Financial markets
Testing

All Science Journal Classification (ASJC) codes

  • Computer Networks and Communications

Cite this

Khirbat, G., Gupta, R., & Singh, S. (2013). Optimal neural network architecture for stock market forecasting. 557-561. Paper presented at 3rd International Conference on Communication Systems and Network Technologies, CSNT 2013, Gwalior, India. https://doi.org/10.1109/CSNT.2013.120
Khirbat, Gitansh ; Gupta, Rahul ; Singh, Sanjay. / Optimal neural network architecture for stock market forecasting. Paper presented at 3rd International Conference on Communication Systems and Network Technologies, CSNT 2013, Gwalior, India.5 p.
@conference{068dc271882f431ea5a451df7183cd04,
title = "Optimal neural network architecture for stock market forecasting",
abstract = "Predicting stocks accurately has always intrigued the market analysts. A possible forecast of stocks is done using trading parameters and Price/Earnings ratio. With the advances in Artificial Neural Networks, it has become possible to analyze a data set in temporal domain. The use of Time Series Forecasting empowers us to predict the value of an entity in the future based on the previously obtained outputs. The current best fit solution for stock forecasting produces a forecast result with 58{\%} accuracy using feed-forward backpropagation neural network. In this paper, we have represented the data set containing financial stock price as a time series. This time series is forecasted by feeding it to a multi layer back propagation neural network. In real world scenario, stock prices are influenced by many non\ deterministic factors such as national & international economy and public confidence. This paper takes into account factors like Earnings Per Share (EPS) and public confidence and introduces an empirically defined neural network architecture of the form [m - m/2 - m/10 - 1] which gives an optimized structure for predicting the future value of a stock by extrapolating the near future value by the present value comparisons. The experimental results obtained after the training and testing of the financial data are very promising. This increase in accuracy of our financial prediction is due to the factors incorporated for forecasting which can give a clear binary classification for buying or withholding the stock in the current market scenario.",
author = "Gitansh Khirbat and Rahul Gupta and Sanjay Singh",
year = "2013",
month = "8",
day = "5",
doi = "10.1109/CSNT.2013.120",
language = "English",
pages = "557--561",
note = "3rd International Conference on Communication Systems and Network Technologies, CSNT 2013 ; Conference date: 06-04-2013 Through 08-04-2013",

}

Khirbat, G, Gupta, R & Singh, S 2013, 'Optimal neural network architecture for stock market forecasting' Paper presented at 3rd International Conference on Communication Systems and Network Technologies, CSNT 2013, Gwalior, India, 06-04-13 - 08-04-13, pp. 557-561. https://doi.org/10.1109/CSNT.2013.120

Optimal neural network architecture for stock market forecasting. / Khirbat, Gitansh; Gupta, Rahul; Singh, Sanjay.

2013. 557-561 Paper presented at 3rd International Conference on Communication Systems and Network Technologies, CSNT 2013, Gwalior, India.

Research output: Contribution to conferencePaper

TY - CONF

T1 - Optimal neural network architecture for stock market forecasting

AU - Khirbat, Gitansh

AU - Gupta, Rahul

AU - Singh, Sanjay

PY - 2013/8/5

Y1 - 2013/8/5

N2 - Predicting stocks accurately has always intrigued the market analysts. A possible forecast of stocks is done using trading parameters and Price/Earnings ratio. With the advances in Artificial Neural Networks, it has become possible to analyze a data set in temporal domain. The use of Time Series Forecasting empowers us to predict the value of an entity in the future based on the previously obtained outputs. The current best fit solution for stock forecasting produces a forecast result with 58% accuracy using feed-forward backpropagation neural network. In this paper, we have represented the data set containing financial stock price as a time series. This time series is forecasted by feeding it to a multi layer back propagation neural network. In real world scenario, stock prices are influenced by many non\ deterministic factors such as national & international economy and public confidence. This paper takes into account factors like Earnings Per Share (EPS) and public confidence and introduces an empirically defined neural network architecture of the form [m - m/2 - m/10 - 1] which gives an optimized structure for predicting the future value of a stock by extrapolating the near future value by the present value comparisons. The experimental results obtained after the training and testing of the financial data are very promising. This increase in accuracy of our financial prediction is due to the factors incorporated for forecasting which can give a clear binary classification for buying or withholding the stock in the current market scenario.

AB - Predicting stocks accurately has always intrigued the market analysts. A possible forecast of stocks is done using trading parameters and Price/Earnings ratio. With the advances in Artificial Neural Networks, it has become possible to analyze a data set in temporal domain. The use of Time Series Forecasting empowers us to predict the value of an entity in the future based on the previously obtained outputs. The current best fit solution for stock forecasting produces a forecast result with 58% accuracy using feed-forward backpropagation neural network. In this paper, we have represented the data set containing financial stock price as a time series. This time series is forecasted by feeding it to a multi layer back propagation neural network. In real world scenario, stock prices are influenced by many non\ deterministic factors such as national & international economy and public confidence. This paper takes into account factors like Earnings Per Share (EPS) and public confidence and introduces an empirically defined neural network architecture of the form [m - m/2 - m/10 - 1] which gives an optimized structure for predicting the future value of a stock by extrapolating the near future value by the present value comparisons. The experimental results obtained after the training and testing of the financial data are very promising. This increase in accuracy of our financial prediction is due to the factors incorporated for forecasting which can give a clear binary classification for buying or withholding the stock in the current market scenario.

UR - http://www.scopus.com/inward/record.url?scp=84880865241&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84880865241&partnerID=8YFLogxK

U2 - 10.1109/CSNT.2013.120

DO - 10.1109/CSNT.2013.120

M3 - Paper

AN - SCOPUS:84880865241

SP - 557

EP - 561

ER -

Khirbat G, Gupta R, Singh S. Optimal neural network architecture for stock market forecasting. 2013. Paper presented at 3rd International Conference on Communication Systems and Network Technologies, CSNT 2013, Gwalior, India. https://doi.org/10.1109/CSNT.2013.120