Nowcasting Indonesia’s GDP Growth Using Machine Learning Algorithms

GDP is very important to be monitored in real time because of its usefulness for policy making. We built and compared the ML models forecast real-time Indonesia's growth. used 18 variables that consist a number quarterly macroeconomic financial market statistics. have evaluated performance six popular algorithms, such as Random Forest, LASSO, Ridge, Elastic Net, Neural Networks, Support Vector Machines, doing on growth from 2013:Q3 2019:Q4 period. RMSE, MAD, Pearson correlation coefficient measurements accuracy. The results showed all these outperformed AR (1) benchmark. individual model best random forest. To gain more accurate result, we run combination using equal weighting lasso regression. was obtained regression with selected models, which are Machine, Network.