COMPARISON OF DOUBLE RANDOM FOREST AND LONG SHORT-TERM MEMORY METHODS FOR ANALYZING ECONOMIC INDICATOR DATA

The performance of machine learning in analyzing time series data is being widely discussed. A new ensemble method Double Random Forest (DRF), which considers supervised currently developed. This has been claimed to be able improve the (RF) if under-fitting. Another method, Long Short-Term Memory Networks (LSTMs) have capability analyze nonlinear data. Since study compare both methods not existed literature, it interesting using Indonesian data, especially economic indicator found under-fitting, non-underfitting, and indicators used this are Export, Import, Official Reserves Asset, Exchange Rate results showed that overall, LSTMs outperforms DRF