ABSTRACT
Stock market prediction plays an important role in financial world. The accurate and reliable prediction results yield high financial benefits to common investors, brokers and speculators. The complex, evolutionary and non linear dynamic behavior of stock market makes it difficult to predict the stock market price. Hence even small improvement in prediction work can be very profitable. Fundamental analysis, technical analysis, time series analysis and statistical analysis are all used for stock prediction but none of these methods are well tried as an acceptable prediction tool. However, there is a need to find adequate methods to predict stock prices. Machine learning techniques have been now popular in predicting stock prices. Technical indicators are effective tools used to predict the trend of stock prices and are considered as good predictive features to machine learning models. The purpose of this paper is to predict the stock prices using Machine Learning Algorithms. The study comprises four prediction models, Naive Bayes, Decision Tree, Random Forest and Decision Tree with AdaBoost and compare the performance of these models in stock price prediction.
