Nowcasting models are an invaluable tool for policymakers and financial professionals, providing timely updates on key economic indicators like gross domestic product (GDP), inflation, employment, and industrial production.
Leveraging RavenPack EDGE Analytics, a state-of-the-art nowcasting model is applied to predict Chinese macroeconomic activity in real time, demonstrating its potential as a powerful forecasting tool.
Observations reveal:
-
The addition of RavenPack Analytics to the model improves performance in terms of the out-of-sample forecasting error by up to 7%, depending on the prediction period.
-
RavenPack Analytics is valuable in terms of timeliness and accuracy, particularly when there is a lack of macroeconomic data.
-
RavenPack Analytics aggregated with a decaying factor over a short horizon (30 days) provides the best contribution as recent events are emphasized.