BCA Share Price Forecasting Using Long Short Term Memory (LSTM)

Abstract

 This research focuses on the development and evaluation of the Long Short-Term Memory (LSTM) model for BCA stock prediction. The LSTM model was chosen for its ability to handle complex time series data and capture underlying temporal patterns. In this study, the LSTM model was trained and tested using BCA stock dataset sourced from Yahoo Finance. The evaluation results show that the LSTM model has excellent prediction performance with Mean Absolute Percentage Error (MAPE) of 1.1244905% and Root Mean Squared Error (RMSE) of 109.78883. The low MAPE value indicates that this model can provide predictions with a very small average error, which is about 1.12% of the actual value. The RMSE value gives an idea of the absolute error rate of the prediction, which in the context of the scale of the data used, indicates a good fit between the predicted and actual values. In conclusion, the developed LSTM model shows great potential for use in stock price prediction. The model can be relied upon to provide accurate predictions and assist in data-driven decision-making. Further research is recommended to optimize this model through techniques such as hyperparameter tuning and coupling with other models to further improve prediction accuracy. In addition, the application of the model to different types of data and different scenarios will expand the generalization and application of the developed LSTM model