AI BASED STOCK PRICE TREND PREDICTION

This research work presented an intelligent stock price trend prediction system using Artificial Intelligence techniques. The proposed model utilizes Long Short-Term Memory (LSTM) neural networks to analyze historical stock market data and identify patterns in time-series information. By learning from past price movements, the system is capable of predicting potential future trends such as uptrend and downtrend. This approach improves the capability of traditional forecasting methods that often struggle with complex and non-linear financial data. A major strength of the proposed system is the integration of technical indicators with deep learning models. Indicators such as Simple Moving Average (SMA), Exponential Moving Average (EMA), Relative Strength Index (RSI), and Moving Average Convergence Divergence (MACD) were incorporated into the prediction process. These indicators provide additional insights about price momentum, market strength, and possible trend reversals. The combination of these indicators with LSTM predictions helps improve the reliability of the overall forecasting process.The system also includes an automated notification module that enhances usability for investors and analysts. When a strong trend signal is detected, the system automatically sends an email alert containing prediction results and indicator confirmations. This feature helps users receive timely updates without continuously monitoring the stock market. As a result, the system becomes more practical and convenient for real-world applications. Experimental results demonstrate that the proposed model performs better than traditional regression-based forecasting approaches. The LSTM network effectively captures long-term dependencies present in stock market time-series data. Performance metrics such as accuracy, Mean Squared Error (MSE), and Root Mean Squared Error (RMSE) indicate improved prediction performance. The inclusion of technical indicators further enhances decision reliability by validating the predictions generated by the deep learning model.Although the proposed system improves prediction accuracy, it is important to understand that stock markets are inherently unpredictable. External factors such as economic conditions, political events, company announcements, and global financial news can significantly influence stock prices. Therefore, the system should be considered as a decision-support tool rather than a fully automated trading solution. Future improvements can further enhance the effectiveness of the system. Potential extensions include integrating real-time stock market data through APIs, incorporating sentiment analysis from financial news and social media, and experimenting with advanced deep learning architectures such as GRU and Transformer models. Additionally, improving model optimization techniques can boost prediction accuracy. Expanding the dataset with diverse market conditions may also strengthen model robustness. Finally, deploying the system as a user-friendly application can increase its practical usability.

1. S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Computation, vol. 9, no. 8, pp. 1735–1780, 1997.   2. G. P. Zhang, “Time series forecasting using a hybrid ARIMA and neural network model,” Neurocomputing, vol. 50, pp. 159–175, 2003.   3. J. Patel, S. Shah, P. Thakkar, and K. Kotecha, “Predicting stock and stock price index movement using trend deterministic data preparation and machine learning techniques,” Expert Systems with Applications, vol. 42, no. 1, pp. 259–268, 2015.   4. T. Fischer and C. Krauss, “Deep learning with LSTM networks for financial market predictions,” European Journal of Operational Research, vol. 270, no. 2, pp. 654–669, 2018.   5. J. Brownlee, Deep Learning for Time Series Forecasting. Machine Learning Mastery, 2017.   6. O. B. Sezer, M. U. Gudelek, and A. M. Ozbayoglu, “Financial time series forecasting with deep learning: A systematic literature review,” Applied Soft Computing, vol. 90, p. 106181, 2020. 7. F. Ahmed and U. Sadiq, “Stock price prediction using LSTM recurrent neural network,” International Journal of Computer Applications, 2020.   8. Y. Zhang and Y. Wu, “Hybrid model for stock price prediction using LSTM and traditional econometric methods,” Journal of Forecasting, vol. 39, no. 5, pp. 637–650, 2020.   9. Y. Chen and Y. Zhang, “Stock price prediction using deep learning: A review,” Journal of Financial Data Science, vol. 2, no. 1, pp. 1–18, 2020.   10. Y. Zhang and J. Wang, “A hybrid LSTM and GRU neural network for stock price forecasting,” Journal of Computer Science and Technology, vol. 35, no. 4, pp. 756–764, 2020.