Long Short-Term Memory Network (LSTM) based Stock Price Prediction

Akshat Gaurav, Varsha Arya, Kwok Tai Chui, Brij B. Gupta, Chang Choi, O-Joun Lee

Abstract: Predicting stock prices is a challenging and highly sought-after task in financial markets. In recent years, deep learning techniques, particularly Long Short-Term Memory (LSTM) networks, have shown promising results in capturing complex temporal dependencies and forecasting time series data. This research paper presents a LSTM-based framework for stock price prediction. The proposed framework utilizes historical stock price data. The LSTM model is designed to learn the underlying patterns and trends in the data, enabling it to make accurate predictions of future stock prices. We preprocess the data, including normalization and feature engineering, to enhance the model's ability to extract meaningful patterns. We employ appropriate evaluation metrics, such as mean squared error (MSE) and root mean squared error (RMSE), to assess the accuracy of the predictions. Experimental results demonstrate that the LSTM-based framework achieves competitive performance in stock price prediction compared to traditional statistical models and other machine learning approaches.