Early Prediction of Real GDP Using the Nowcasting Model


December 01, 2022

  • Shotaro Kugo


◆In recent years, the nowcasting model has attracted attention as a means of grasping real GDP at an early stage, as evidenced by the announcement of predictive values of the GDP nowcasting model by Hayashi and Tachi (2022) and Urasawa (2021). In this report, we constructed a GDP nowcasting model with a combination of traditional econometric methods and machine learning.

◆Furthermore, for some macroeconomic statistics, we attempted to capture fluctuations in economic activity at an earlier stage by incorporating estimates obtained from quick-release data into the model, such as alternative data and industry statistics. The accuracy of real GDP forecasts based on the model thus constructed exceeded the accuracy of market forecasts, suggesting that the model is a useful tool for early grasping of real GDP. However, issues remain, such as the tendency for the gap between the predicted value based on the GDP nowcasting model and the actual real GDP growth rate to be large after the Corona Crisis.

Daiwa Institute of Research Ltd. reserves all copyrights of this content.
Copyright permission of Daiwa Institute of Research Ltd. is required in case of any reprint, translation, adaptation or abridgment under the copyright law. It is illegal to reprint, translate, adapt, or abridge this material without the permission of Daiwa Institute of Research Ltd., and to quote this material represents a failure to abide by this act. Legal action may be taken for any copyright infringements. The organization name and title of the author described above are as of today.