Literature Review: Machine Learning in Stock Predictions

Abstract

Machine learning has revolutionized the field of stock prediction by offering a wide range of models capable of handling complex patterns and making accurate forecasts. Machine learning models vary widely in their application, uses, and effectiveness, and stocks vary as well in terms of volatility within the stock and also between stocks of different industries and at different market conditions. As such, the selection of the proper algorithmic tool to aid an investor is often difficult. This literature review paper provides an overview of ten popular machine learning models over two problem types (prediction and classification), namely Linear Regression, XGBoost, LSTM, ARIMA, GARCH, Random Forest, Logistic Regression, Adaboost, GRU, and CNN. By providing an exploration of these ten machine learning models, this literature review offers valuable insights into their underlying principles, applications and uses, results strengths, and limitations. This paper equally, by consequent, facilitates informed decision-making and encourages further research in the field of machine learning.