Prediction of Stock Market Performance Analysis by Using Machine Learning Regressor Techniques

Abstract

Stock market prediction is a widely researched and crucial topic for investors, traders, and financial analysts. Precisely predicting stock price fluctuations can aid in making informed decisions regarding the buying or selling of stocks. One approach to achieving this is through sentimental analysis that has emerged as a popular approach for predicting stock prices. The research employs machine learning methods to enhance the accuracy of stock market predictions.. It focuses on analyzing the efficiency of five advanced machine learning regression model:

Bagging Regressor, XGB Regressor, LGBM Regressor, Hist Gradient Boosting Regressor, and AdaBoost Regressors are widely used models in machine learning applied to regression tasks. Out of these models, the Bagging Regressor stood out by delivering the best performance, with an R-squared score of 99.9774 and a minimal RMSE of 8.305. It also proved to be computationally efficient, completing the task in just 0.1857 milliseconds. These results emphasize the dependability and effective of the Bagging method Regressor in stock market prediction in Providing meaningful insights for financial modeling and decision-making.