Paper Contents
Abstract
This study uses a deep learning method to predict stock price changes with Attention-Based Deep Neural Network. Traditional models like LSTM and GRU often have trouble for understanding long-term pattern in financial data. The attention mechanism helps the model focus on the most important past data, making predictions more accurate and easier to interpret. Using historical stock prices and technical indicators from the National Stock Exchange (NSE) of India, the proposed model achieves 93.2% prediction accuracy which is better than LSTM (89.5%) and GRU (88.7%). This shows the attention-based deep learning can be useful tool for creating smart and reliable financial forecasting.
Copyright
Copyright © 2025 Kranti kadam, Rutuja Deshmukh, Prof. Tushar Kathane. This is an open access article distributed under the Creative Commons Attribution License.
