An Comparative Study of Machine Learning Models for Stock Market Rate Prediction

Predicting the direction of movement of the stock market index is important for the development of effective market trading strategies. It usually affects a financial trader’s decision to buy or sell a stock. Closing price is one of the important factors in effective stock trading. Successful prediction of closing stock prices may promise attractive benefits for investors. Machine learning techniques have potential capability to process the historical stock trends and predict near accurate closing prices. This study compares three diverse machine learning models – ARIMA time series forecasting model, Support Vector Regression and LSTM Neural Network in terms of complexity of analysis, predictive accuracy for closing prices and customization.