Long-Short Term Memory Based Stock Market Analysis

• Main Authors: Choudhury, Shounak, Basak, Saptarshee, Roy, Saumik, Das, Amit Kumar
• Format: Conference Proceeding
• Language: English
• Subjects: forecasting; LSTM (Long Short Term Memory); MAE(Mean Standard Error); modeling; RMSE(Root Mean Square Error); RNN(Recurrent Neural Network); robustness
• ISSN: 2767-9934
• DOI: 10.1109/IEMENTech60402.2023.10423465

Stock market Prediction has been a source of much interest and challenge in financial markets for a long time. In this study we shall investigate the use of long term and short term memory network (LSTM), a type of Recurrent Neural Network (RNN) for stock market forecasting. Long Short Term Memory (LSTM) has shown promising results in time series analysis. They have the ability to learn long term dependencies in time series data, making them well suited for modeling the temporal patterns of stock prices. The main aim of this project is to predict the stock price trend in the future according to various time frame and factor with accuracy and robustness of the Long Short Term Memory(LSTM) model and also to find the performances indices such as Mean Standard Error(MAE) and Root Mean Square Error(RMSE).The basic Novelty of this design of the Long Short Term Memory(LSTM) model in our work is that it ensures a minimum level of time and space complexity and the model can make highly accurate and precision predictions from a large dataset and is not affected much by fluctuations due to the root mean square and mean absolute error algorithms present in the design.