Flash Estimates of Household Final Consumption Expenditure in East Java

The purpose of this study is to construct a flash estimates model for household final consumption expenditure in East Java. There were 153 indicators that used, covering Big Data and non indicators. Indicators from the Google Trends categories selected based on highest correlation coefficient. While total deposit, credit, consumer lending rate, term deposit rate (1, 3, 6 months), withdrawal (outflow), Consumer Price Index (CPI). This examines several models: ARIMA, ADL, Elastic Net, Support Vector Machine, Random Forest Ensemble. models examined using various scenarios out-of-sample estimation periods (t+10 days, t+20 days t+30 days). prediction performance evaluated Root Mean Squared Error (RMSE) Absolute Percentage (MAPE). evaluation results showed Net Ensemble best any scenarios. Both had good since t+10 days.