The stock market is a dynamic and complex financial arena where individuals and organizations can trade shares of publicly listed companies. It serves as a platform for companies to raise funds for expansion and innovation, while also providing opportunities for investors to grow their wealth. The Seminar focuses on using a type of neural network called Long Short-Term Memory (LSTM) to predict stock prices. The stock market is known for its complexity and volatility, which makes accurate predictions a challenging task. However, LSTM networks have gained popularity due to their ability to capture long-term patterns in sequential data, making them suitable for modeling time series data like stock prices. In this Seminar, historical stock price data is collected and prepared for input into the LSTM model. The LSTM architecture is then built, consisting of multiple LSTM layers followed by a dense output layer. Dropout regularization is applied to prevent the model from overfitting the training data and to enhance its generalization capability. The constructed LSTM model is trained using the historical stock price data, and its performance is evaluated using separate test data that the model has not seen before. Evaluation metrics such as mean squared error and accuracy are used to measure the model's predictive ability. The experimental results demonstrate that the LSTM model is effective in predicting stock prices. The model achieves promising accuracy and demonstrates its ability to identify patterns and trends in the stock market data. These findings contribute to the existing research on using deep learning techniques, like LSTM, for forecasting financial time series.
Keywords: - LSTM, ANN, Stock Market, Technical indicators, Neural networks, Financial Data, Time series Analysis