Published Paper Details:

Predicting stock market trends is a challenging task due to the highly volatile and nonlinear nature of financial data. Traditional forecasting models often struggle to capture complex market patterns, necessitating the adoption of advanced machine learning and deep learning approaches. This study presents a comprehensive stock price prediction system that integrates AutoRegressive Integrated Moving Average (ARIMA), Long Short-Term Memory (LSTM) networks, and Linear Regression models for enhanced forecasting accuracy. Additionally, sentiment analysis is incorporated to assess market sentiment using social media data, providing deeper insights into stock price fluctuations.The ARIMA model is employed for time-series forecasting, effectively capturing linear trends, while LSTM, a deep learning architecture, is used to learn long-term dependencies in stock price movements. Linear Regression serves as a statistical approach for trend estimation. Sentiment analysis, conducted using TextBlob and Twitter API, enables the evaluation of public perception, further refining stock predictions. The system is deployed as a Flask-based web application, allowing users to perform real-time stock analysis.Experimental findings indicate that LSTM outperforms ARIMA and Linear Regression in capturing intricate stock price variations, while sentiment analysis provides valuable supplementary information for trend forecasting. This research underscores the significance of combining time-series analysis, deep learning techniques, and sentiment analysis to improve stock market prediction reliability. Future enhancements may include the integration of additional financial indicators and real-time data streams for greater predictive accuracy.