A prediction based approach for stock returns using autoregressive neural networks

Author

Rather, Akhter Mohiuddin

Author_Institution

Dept. of Comput. & Inf. Sci., Univ. of Hyderabad, Hyderabad, India

fYear

2011

fDate

11-14 Dec. 2011

Firstpage

1271

Lastpage

1275

Abstract

This paper presents a prediction based neural networks approach for stock returns. An autoregressive neural network predictor is used to predict future stock returns. In this predictor, the differences between the values of the series of stock returns and a specified past value are the regression variables. Various error metrics have been used to evaluate the performance of the predictor. Experiments with real data from National stock exchange of India (NSE) were employed to examine the accuracy of this method.

Keywords

autoregressive processes; economic forecasting; neural nets; performance evaluation; regression analysis; stock markets; NSE; National stock exchange of India; autoregressive neural network predictor; autoregressive neural networks; error metrics; future stock returns; performance evaluation; prediction based approach; prediction based neural networks approach; regression variables; Autoregressive processes; Biological neural networks; Forecasting; Neurons; Predictive models; Time series analysis; Autoregressive neural networks; Backpropagation neural network; Stock returns; Time series prediction;

fLanguage

English

Publisher

ieee

Conference_Titel

Information and Communication Technologies (WICT), 2011 World Congress on

Conference_Location

Mumbai

Print_ISBN

978-1-4673-0127-5

Type

conf

DOI

10.1109/WICT.2011.6141431

Filename

6141431