Machine Learning Techniques For Stock Price Prediction - A Comparative Analysis Of Linear Regression, Random Forest, And Support Vector Regression

Abstract

In the dynamic and rapidly evolving stock market, the ability to generate accurate and timely predictions holds paramount significance for companies and investors alike. Machine learning algorithms can identify complex patterns in the stock market. Machine learning algorithms play a critical role in this situation, leveraging their capacity to analyze extensive datasets and provide valuable insights, thereby forecasting future trends. Stock price prediction is still an arduous task because of the financial markets' well-known volatility. In recent years, there has been a significant increase in the use of machine learning techniques for stock price prediction. This is because these algorithms can handle large amounts of data and identify complex patterns that are difficult for humans to recognize. The proposed methodology focuses on using linear regression (LR), support vector regression (SVR), and random forest machine learning models to predict Tata Consultancy Services (TCS) stock prices. Machine learning presents a promising method in this field of stock price prediction, which is essential for traders and investors to make well-informed judgements. via data on TCS stock prices, the study evaluates the models via feature engineering and hyperparameter tuning. An understanding of how well these algorithms anticipate stock values is given by the analysis and findings. Mean Squared Error (MSE) and Root Mean Squared Error (RMSE) standard metrics are used to compare the time series data. After Applying hyperparameter tuning on Support Vector Regression and Random Forest the standard metrics RMSE shows decrease in error rate. In the proposed model Linear Regression has better performance than Support Vector Regression and Random Forest.