Machine Learning in Stock Market Prediction: A Review

Abstract

Predicting the stock price has always been a topic of great interest to both investors and researchers. Machine learning algorithms combined with massive volumes of financial data have proven to be useful tools for stock prediction. However, as the efficient market hypothesis says, market cannot be entirely predicted so it is extremely difficult to apply the findings of these studies to realworld investment trading techniques and make price predictions. This paper represents a brief overview of machine learning techniques for prediction of the stock closing price as well as the direction of stock’s future price movement. In this study, machine learning techniques including the Random Forest, Support Vector Machine (SVM), and Long Short-Term Memory Neural Network (LSTM) were explored and compared carefully. Finally, the study discusses the limitations of each technique and their application in real-world problems.

Keywords: Stock Market, Price Prediction, Machine Learning, Random Forest, Support Vector Machine (SVM), and Long Short-Term Memory Neural Network (LSTM)