StockAI: An Intelligent Stock Market Prediction and Analysis Platform Using Machine Learning and Conversational AI

This paper presented StockAI, an intelligent stock market prediction and analysis system that integrates machine learning techniques with a conversational user interface. The system was designed to assist users in understanding market behaviour and making informed investment-related decisions using data-driven insights. A Random Forest classifier was implemented using ten years of historical stock data from 100 US-listed companies. The model utilized multiple technical indicators such as moving averages, RSI, MACD, volatility, and momentum to generate Buy and Sell predictions across different time horizons. Experimental results showed that the system achieved an average accuracy of approximately 60–62% across 5-day, 20-day, and 120-day prediction intervals. Although stock market prediction is inherently complex due to its volatile and non-linear nature, the proposed system demonstrated consistent performance and meaningful predictive capability. The inclusion of confidence scores further enhanced decision support by allowing users to evaluate the reliability of predictions. In addition, the integration of a chatbot-based interface made the system more accessible to non-technical users by enabling natural language interaction with the prediction engine. Overall, StockAI successfully combines machine learning, technical analysis, and conversational AI into a unified platform for financial analysis.

[1] Breiman, L., “Random Forests,” Machine Learning, vol. 45, no. 1, pp. 5–32, 2001. [2] Hochreiter, S., and Schmidhuber, J., “Long Short-Term Memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997. [3] Pedregosa, F., et al., “Scikit-learn: Machine Learning in Python,” Journal of Machine Learning Research, vol. 12, pp. 2825–2830, 2011. [4] McKinney, W., “Data Structures for Statistical Computing in Python,” Proceedings of the 9th Python in Science Conference, 2010. [5] Hunter, J. D., “Matplotlib: A 2D Graphics Environment,” Computing in Science & Engineering, vol. 9, no. 3, pp. 90–95, 2007. [6] Huang, C., et al., “Stock Market Prediction Using Machine Learning Techniques,” International Journal of Computer Applications, 2020. [7] Devlin, J., Chang, M. W., Lee, K., and Toutanova, K., “BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding,” NAACL, 2019. [8] Kearns, M., and Nevmyvaka, Y., “Machine Learning for Financial Trading,” ICML Workshop on Machine Learning in Finance, 2013. [9] yFinance Documentation, “Yahoo Finance API for Python,” Available: https://pypi.org/project/yfinance/ [10] TA Library Documentation, “Technical Analysis Library in Python,” Available: https://technical-analysis-library-in-python.readthedocs.io/