Abstract
Recently, the stock market has experienced significant instability, especially during the global pandemic which resulted in unprecedented economic impact. The main focus of this research is to develop an optimal prediction model using deep learning techniques for the projection of closing prices of bank stocks during the pandemic period. This study evaluates the performance of banking stocks, specifically ARTO, BRIS, BBNI, and BMRI in the Jakarta Composite Index (JCI). Data was extracted from Yahoo Finance and processed through LSTM and GRU algorithms, including data cleaning, normalisation, and descriptive statistical analysis. Scoring metrics such as MSE, RMSE, and MAPE are used to measure the effectiveness of the predictive models. The results show that the LSTM and GRU models can predict stock prices well. These findings provide a basis for trading strategies and improved decision-making in the stock market. Recent research confirms the importance of integrating deep learning methods such as LSTM and GRU in stock price prediction, helping to understand complex financial market fluctuations and improve prediction accuracy.
Published Version
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call