Identifying Significant Macroeconomic Indicators for Indian Stock Markets

Aithal, Prakash K and Acharya, Dinesh U and Geetha, M (2019) Identifying Significant Macroeconomic Indicators for Indian Stock Markets. IEEE Access, 7. pp. 143829-143840. ISSN 2169-3536

[img] PDF
7632.pdf - Published Version
Restricted to Registered users only

Download (8MB) | Request a copy

Abstract

The macroeconomic indicators play a major role in all the stock markets, and they vary from nation to nation. This paper identifies the influence of macroeconomic indicators on the National Stock Exchange (NSE) and the Bombay Stock Exchange (BSE) of India. Total of forty-four macroeconomic indicators for eight years from the year 2011 to 2018 are considered in this study. The macroeconomic factors are aggregated and considered in average monthly form. The proposed method finds the correlation matrixofallconsideredmacroeconomicindicators.Theneedfordimensionalityreductionandtheexistence of multicollinearity are proven using validation techniques such as the Kaiser-Meyer-Olkin and Bartlett tests. The Principal Component Analysis (PCA) method is used to reduce the dimensionality to seven factors and then PCA with the varimax rotation method is applied to find factors with maximum variation. In addition, the influence of these seven factors on the NSE Nifty and BSE SENSEX indices are analyzed using regression. Finally, an Artificial Neural Network is used to predict stock market movement with the help of macroeconomic indicators. Accuracy of 92% and 87% are obtained on NSE NIFTY and BSE SENSEX respectively.

Item Type: Article
Uncontrolled Keywords: Decision support systems, knowledge discovery, macroeconomic indicators, principal component analysis, arti�cial neural network, data mining.
Subjects: Engineering > MIT Manipal > Computer Science and Engineering
Depositing User: MIT Library
Date Deposited: 14 Dec 2019 04:37
Last Modified: 14 Dec 2019 04:37
URI: http://eprints.manipal.edu/id/eprint/154758

Actions (login required)

View Item View Item