Stock Market Prediction using Machine Learning Techniques

Abstract

Prediction of Stock Market has been an area of interest for investors as well as researchers from a long time due to its intrinsic volatility, complex and regularly changing in nature makes it difficult to make reliable prediction. So, predicting daily behaviour of stock market is a serious challenge for investors and corporate stockholders. The objective of this paper is to predict the market performance by using Artificial Neural Network. These techniques are used to classify the stock in 3 categories – Buy, Hold and Sell, based on historical data while providing an in-depth understanding of the models being used. The Study shows that logistic regression model compared to Linear Regression can be used by the investors, individual as well as fund managers to predict “good or poor” stock. Because of the data being Non-Linear we will be using artificial neural network to classify Non-linear data using hidden layers.