Abstract

Stock market forecasting is a difficult task because of the volatility and unpredictable nature of financial data. To address this is-sue, we present an AI-based Stock Prediction Model that predicts future stock prices by analyzing historical data, trading volume, and price movements. Our model captures temporal dependence and finds connections within financial time series using machine learning techniques. Additionally, a sentiment analysis module processes financial news and classifies public sentiment as positive, negative, or neutral, which provides context to the market. Our model is designed as a web application using Python and Flask, making it user-friendly and allowing for analysis and visualization of continuously updated data. Our experimental results show that the model connects past market behavior to future trends, enabling better-informed decisions. In summary, our work emphasizes the value of AI-based predictive analytics in finance for making informed and timely investment choices.

References

• N. Zhang, “Stock Market Prediction with Deep Learning Models,” Procedia Computer Science, vol. 224, pp. 1139–1146, 2023.
• J. Patel, S. Shah, P. Thakkar, and K. Kotecha, “Predicting Stock Market Index Using Machine Learning Techniques,” Expert Systems with Applications, vol. 42, no. 4, pp. 2162–2172, 2022.
• Musale, J. C., Zad, P., Nawale, S. J., Kokare, G., & Niture, S. “Stock Market Prediction Using Machine Learning”. In Multifaceted Approaches for Data Acquisition, Processing and Communication, CRC Press, 2024, pp. 248–256. DOI: 10.1201/9781003470939-32
• S. Kumar and R. Roy, “Financial Sentiment Analysis and Its Impact on Stock Prediction,” IEEE Access, vol. 11, pp. 54120–54135, 2023.
• Y. Liu, I. Lee, and H. Wang, “FinBERT: A Pretrained Language Model for Financial Sentiment Analysis,” arXiv preprint arXiv:2006.08097, 2020.
• H. Nelson and J. Kim, “Stock Price Prediction Using LSTM Recurrent Neural Networks,” IEEE Access, vol. 10, pp. 54021–54032, 2022.
• S. Li, X. Li, and J. Liu, “Integrating Sentiment Analysis with Stock Market Prediction Using Deep Learning,” IEEE Trans-actions on Computational Social Systems, vol. 9, no. 2, pp. 411–422, 2022.
• Musale, J. C., et al. “Enhancing Web Traffic Security: A Deep Learning Approach to Defend Against Traffic Analysis Attack”. IEEE Conference, 2024. DOI: 10.1109/emer-gin63207.2024.10961562
• T. Wang and Y. Xu, “Multimodal Deep Learning for Stock Prediction Based on News and Price Data,” Neural Comput-ing and Applications, vol. 35, pp. 1783–1797, 2023.
• M. Gupta, N. Jain, and R. Mehta, “AI-Driven Financial An-alytics: Correlation of Market Indicators with News Sentiment,” in Proc. IEEE ICCIDS, pp. 1–6, 2023.
• S. Dutta and M. Das, “Sentiment Analysis of Financial News Using Transformer-Based Deep Learning Models,” International Journal of Intelligent Engineering and Systems, vol. 15, no. 6, pp. 245–253, 2022.
• R. Thakkar and P. Chaudhari, “Fusion of News Sentiment and Historical Data for Stock Market Forecasting Using Machine Learning,” Journal of King Saud University – Computer and Information Sciences, vol. 34, no. , pp. 2718–2728, 2022.