Stock Price Prediction of PT. Pertamina Geothermal Energy Tbk Using Gated Recurrent Unit (GRU) Model

Abstract

This study aims to predict the stock price of PT. Pertamina Geothermal Energy Tbk (PGEO.JK) using the Gated Recurrent Unit (GRU) model, a neural network architecture in the Recurrent Neural Network (RNN) category that is known to be effective in handling time series data. The data used is historical stock price data from 2022 to 2024 taken from Yahoo Finance. The GRU method was chosen because of its ability to remember long-term information and overcome the vanishing gradient problem. In the research process, the data was divided into two parts, namely training data and testing data. The GRU model was trained without adjusting hyperparameters to measure its performance by default. Model evaluation was carried out using the Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), and coefficient of determination (R²) metrics. The results of the study indicate that the GRU model is able to provide good prediction results with an RMSE value of 0.0271, MAE of 0.0180, MAPE of 22.25%, and an R² value of 0.9112. These values ​​indicate that the GRU model is quite accurate in predicting the price of PGEO.JK shares. These findings indicate that GRU is a potential method in stock prediction analysis, especially in the renewable energy sector.