Published Paper Details:

The stock market plays a crucial role in a country's financial growth, but it is also highly dynamic and unpredictable. It can be influenced rapidly by various factors such as political developments, investor sentiment, media reports, company restructuring, and growth strategies. Every trading day, thousands of investors participate in the stock market--some gain profits, while others incur losses. However, predicting these gains or losses on any given day remains a significant challenge. This research presents a web-based application developed for predicting stock market trends through the implementation of machine learning techniques. The system integrates both historical stock data and real-time data obtained from APIs, and employs three robust predictive models--ARIMA (Auto Regressive Integrated Moving Average), LSTM (Long Short-Term Memory), and Linear Regression. These models are utilized to forecast the closing price for the next trading day, as well as to provide projections for the subsequent seven days. By analyzing historical patterns and trends in the data, the models aim to extrapolate future price movements with improved precision. The integration of numerical data analysis significantly enhances the overall accuracy and reliability of the stock price predictions generated by the system.