A Comparative Study of the Stock Market using Machine Learning Algorithms

The purpose of this review work is to present a strategy for accurate stock price prediction in the face of multiple factors affecting stock prices. The strategy involves the utilization of four efficient machine learning models - K-Nearest Neighbors (KNN), Naive Bayes, SVM classifiers, and Random Forest classifiers - to analyze and forecast stock values under various market conditions. The performance of the proposed strategy is evaluated through the comparison of accuracy, precision, and recall metrics using a stock price dataset. The intention of this review paper is to provide a comprehensive solution to the challenge of stock prediction by utilizing multiple machine learning algorithms in different scenarios. The framework is then assessed and predicted for its classification accuracy, which will help to overcome the complexities in the stock prediction process and provide a robust and reliable approach to stock price forecasting.