REAL-TIME STOCK MARKET PRICE PREDICTION USING MACHINE LEARNING

Abstract

After the COVID-19 ended, the global economy gradually recovered. Due to the nonlinearity, complexity, and high noise of financial time series, stock price prediction has become one of the most challenging tasks in the stock market. we propose a real-time stock market price prediction based on Long Short-Term Memory (LSTM) to simultaneously improve the fitting and accuracy of stock price prediction. Key algorithms like LSTM (Long Short-Term Memory), ARIMA (Auto Regressive Integrated Moving Average), and Random Forest will be explored for their effectiveness in forecasting stock trends. Data preprocessing and feature engineering techniques are applied to improve model reliability and prediction accuracy. The developed system integrates an interactive dashboard that visualizes both historical and predicted stock trends, enabling users to monitor market movements and gain insights into potential price behavior. By combining machine learning models with real-time data acquisition and visualization, the proposed approach provides a practical tool for supporting data-driven financial analysis and decision-making.