Abstract
Forecasting the U.S. employment level is made using machine learning methods of the artificial neural network: deep neural network, long short term memory (LSTM), gated recurrent unit (GRU). We consider the big data of the federal reserve economic data among which 105 important macroeconomic variables chosen by Mc- Cracken and Ng (Journal of Business and Economic Statistics, 34, 574-589, 2016) are considered as predictors. We investigate the influence of the two statistical issues of the dimension reduction and time series differencing on the machine learning forecast. An out-of-sample forecast comparison shows that (LSTM, GRU) with differencing performs better than the autoregressive model and the dimension reduction improves long-term forecasts and some short-term forecasts.
| Original language | English |
|---|---|
| Pages (from-to) | 497-506 |
| Number of pages | 10 |
| Journal | Communications for Statistical Applications and Methods |
| Volume | 26 |
| Issue number | 5 |
| DOIs | |
| State | Published - 2019 |
Bibliographical note
Funding Information:This study was supported by a grant from the National Research Foundation of Korea (2019R1A2C10 04679), by the Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Education (2019R1A6A1A11051177) and by the Ewha Womans University Scholarship of 2017.
Publisher Copyright:
© 2019 The Korean Statistical Society, and Korean International Statistical Society. All rights reserved.
Keywords
- Deep neural network
- Differencing
- Dimension reduction
- Employment forecast
- Gated recurrent unit
- Long short term memory