Model Dynamic Ensemble Time Series untuk Prediksi Indeks Harga Saham Utama di Indonesia Pasca Pandemi

Abstract

Forecasting or predicting stock prices in the form of time series data is still a hot topic consistently discussed in economic forums and financial markets. This article had been analyzed prediction of stock prices in Indonesia after experiencing a pandemic and one year after the Corona virus. This study had been applied a dynamic ensemble method that combines various prediction models to improve forecasting accuracy. The results showed that the model has a high level of accuracy with MAPE (Mean Absolute Percentage Error) values of 0.003714125, and RMSE (Root Mean Square Error) of 0.03958605. Furthermore, these results could be used as a basis for government policy making and stock investment decisions for investors.