Stock Price Prediction on Indian Share Market Using Machine Learning

Since the development of machine learning, predicting stock market trends has become a captivating task, impacted by economic data, politics, and investor mood. The complexity of these components makes reliable prediction challenging. In this work, we analyze multiple models, including statistics, linear regression, and deep learning, using a 10-year dataset of Asian Paints stock prices from the BSE also our results reveal that LSTM beat other models with an R2 score of 94.5, followed by RNN at 93, and this illustrates LSTM's capacity to capture long-term dependencies in stock price prediction. By utilizing rigorous measurements, we uncover model strengths and flaws, improving decision-making for academics and practitioners. Deep learning, particularly LSTM, gives useful insights for comprehending stock market difficulties, and further advances are conceivable through new features and political sentiment research. Our research intends to increase trust in decision-making for investors, financial analysts, and policymakers, highlighting the potential of deep learning.