Prediksi Pergerakan Saham BBRI ditengah Issue Ancaman Resesi 2023 dengan Pendekatan Machine Learning

Abstract

The economic recovery after the Covid-19 pandemic is becoming increasingly challenging. According to several experts, a global recession is expected to occur in 2023, necessitating contributions from various fields of knowledge to address this situation. Machine learning is one method that can contribute by forecasting stock price movements. This research attempts to address the issues faced by traders in observing the potential movement of BBRI stock under the recession issue in 2023. Furthermore, this study uses linear regression and Bayesian regression methods to find the best model. By using six-month stock data of BBRI, with attributes such as open, high, low, and close as prediction targets, it is found that the model built using linear regression outperforms Bayesian regression. Based on the testing results, the linear regression model achieved a Dstat of 80% and an RMSE of 595.30, while the Bayesian regression model obtained a Dstat of 80% but a higher RMSE of 660.58. Based on the modeling results in this study, it is concluded that in the first semester of 2023, BBRI stock is still moving upward and is not affected by the recession issue in 2023.