Stock Prediction using Artificial Neural Network; Evidence with Nifty 50 IT Companies Gnanendra M*, Jana Jesna** *Assistant Professor, Department of Management Studies, Christ. gnanendra.m@christuniversity.in **Student, Department of Management Studies, Christ. jesna.jana@bba.christuniversity.in Online published on 11 April, 2018. Abstract This study aims at reducing investors risk in trading by predicting the stock prices accurately. The research methodology used here is Multi-Layer Perceptron in neural networks, which is one of the artificial neural network model. Artificial Neural Network models are highly flexible functional algorithms evolved using machine's cognitive learning. Recently there has been huge increase in neural network applications. For many applications like pattern recognition, time series analysis, classification etc. In this we are predicting the stock prices of Nifty 50 IT companies, where closing prices of each stock for over 10 years is been predicted using the independent variables like average price, volume of trade, No. of trade, and total traded quantity. The series has been divided into training data and testing data to arrive at the most accurate closing price. The frequency of given variable is daily, hence it would provide for a more efficient and would include daily volatility. The results of this study show that the prediction method used with the help of neural networks is a very conducive model for stock price prediction. Top Keywords Artificial neural network, Multi-Layer Perceptron, stock price prediction, Machine Learning, NSE 50 IT. Top |