Open AccessModel Dynamic Ensemble Time Series untuk Prediksi Indeks Harga Saham Utama di Indonesia Pasca Pandemi
Author(s) -
Evita Purnaningrum
Publication year - 2021
Publication title -
majalah ekonomi/ekonomi
Language(s) - English
Resource type - Journals
eISSN - 2776-2165
pISSN - 1411-9501
DOI - 10.36456/majeko.vol26.no1.a3949
Subject(s) - mean absolute percentage error , mean squared error , stock (firearms) , econometrics , time series , economics , statistics , finance , mathematics , engineering , mechanical engineering
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.