PREDICTING STOCK MARKET PRICE BY USING ARTIFICIAL NEURAL NETWORK TRAINED WITH FOUR DIFFERENT ALGORITHM: A PILOT STUDY OF 15 BANGLADESHI COMPANY
No Thumbnail Available
Date
2021-03-30
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Abstract
Stock market price prediction is now a popular and important topic in financial and
academic studies because stock market plays a vital rule in economy. Stock market price
prediction is the act of trying to determine the future value of company stock. Stock market
prices are actually time-series data and Artificial Neural Networks (ANNs) have the ability
to find non-linear correlations between time-series data which makes it the best approach
to predict stock market prices. Many researchers working on this topic and try to find the
best algorithm with using stock market dataset which is suitable for predicting stock price.
In this research historical data from Dhaka Stock Exchange is used to train and predict the
price by using ANN. The Artificial Neural Network (ANN) is implemented by using
multilayer Feedforward backpropagation model. In this paper fifteen companies six years
data have been analyzed. To predict the specific result, the model has been trained in four
different algorithm with change their parameter. Number of hidden layer, hidden neuron
and percentage of training data have been change to get better output. After the training
and testing process the predicted values are compared with the real data to find the
accuracy. The trained network with the highest accuracy rate will able to predict the best
possible price of the stock market.