STOCK MARKET DATA ANALYSIS AND PREDICTION MODELING USING MACHINE LEARNING TECHNIQUES

Stock market prediction is one of the most important and time-consuming processes in the financial sector. This is mainly because many factors could influence particular stock prices dynamically. In recent days, algorithm-based predictions have become widely popular among researchers because it provides better results in terms of improved accuracy and reduced error rates. That in turn helps the investors to make precise and informed decisions. In this study, a comparative analysis of various machine learning models was performed, and the results were evaluated based on performance metrics such as mean square error (MSE), root mean square error (RMSE), mean absolute error (MAE), mean absolute percentage error (MAPE) and accuracy. The objective of this comparative study is to help investors take better decisions based on the consistent results provided by the algorithmic models. This project involves various machine learning models to predict stock prices — Linear Regression, Decision Trees, Random Forests and Support Vector Machines(SVM) as well deep learning methods like Long Short-Term Memory (LSTMs). Results show that compared to traditional techniques have up shots of accuracy and adaptability with market change in machine learning methods, deep-leaning models are significantly better. With the observation that no model can predict stock prices well enough because of the randomness in market, but ML is a great tool to help provide edge for prediction aiding traders and investors take more informed decisions.