Predicting Stock Market Price Using Neural Network Model

Predicting Stock Market Price Using Neural Network Model

Naliniprava Tripathy (Indian Institute of Management Shillong, Shillong, India)
Copyright: © 2018 |Pages: 11
DOI: 10.4018/IJSDS.2018070104
OnDemand PDF Download:
No Current Special Offers


The present article predicts the movement of daily Indian stock market (S&P CNX Nifty) price by using Feedforward Neural Network Model over a period of eight years from January 1st 2008 to April 8th 2016. The prediction accuracy of the model is accessed by normalized mean square error (NMSE) and sign correctness percentage (SCP) measure. The study indicates that the predicted output is very close to actual data since the normalized error of one-day lag is 0.02. The analysis further shows that 60 percent accuracy found in the prediction of the direction of daily movement of Indian stock market price after the financial crises period 2008. The study indicates that the predictive power of the feedforward neural network models reasonably influenced by one-day lag stock market price. Hence, the validity of an efficient market hypothesis does not hold in practice in the Indian stock market. This article is quite useful to the investors, professional traders and regulators for understanding the effectiveness of Indian stock market to take appropriate investment decision in the stock market.
Article Preview

2. Literature Review

Several studies have predicted the stock market price in the past decades. Min Qi (1999) examined the forecasting ability of the United States (US) stock market returns by using Linear Regression and Nonlinear Neural Network model. The study found that the Nonlinear NN model fits data better than the linear model and provides relatively accurate forecast than the linear model. Phua, et al. (2000) used NN with Genetic Algorithm to predict the Singapore stock market. The study found that the model predicts 81 percent accuracy of the direction of the stock market. Yochanan and Dorota (2000) examined the dynamic interrelations among Canada, France, Germany, Japan, United Kingdom (UK), US and World stock markets by using Ordinary Least Squares, General Linear Regression, Multi-layer Perceptron models of ANN. The study reported that NN consist of Multilayer perceptron model with logistic activation function predicts the daily stock market returns better than traditional Ordinary Least Squares and General Linear Regression model. The Multilayer Perceptron, with five units in the hidden layer, better predicts the stock indices of US, France, Germany, UK and World stock markets.

Complete Article List

Search this Journal:
Volume 14: 1 Issue (2023): Forthcoming, Available for Pre-Order
Volume 13: 4 Issues (2022): 1 Released, 3 Forthcoming
Volume 12: 3 Issues (2021)
Volume 11: 4 Issues (2020)
Volume 10: 4 Issues (2019)
Volume 9: 4 Issues (2018)
Volume 8: 4 Issues (2017)
Volume 7: 4 Issues (2016)
Volume 6: 4 Issues (2015)
Volume 5: 4 Issues (2014)
Volume 4: 4 Issues (2013)
Volume 3: 4 Issues (2012)
Volume 2: 4 Issues (2011)
Volume 1: 4 Issues (2010)
View Complete Journal Contents Listing