What is it about?

We present a machine-learning method for sentiment indicators construction that allows an automated variable selection procedure. By means of genetic programming, we generate country-specific business and consumer confidence indicators for thirteen European economies and for the Euro Area. The algorithm finds non-linear combinations of qualitative survey expectations that yield estimates of the expected rate of quarter-on-quarter GDP growth.

Featured Image

Why is it important?

We find that firms’ production expectations and consumers’ expectations to spend on home improvements are the most frequently selected variables – both lagged and contemporaneous. To assess the performance of the proposed approach, we have designed an out-of-sample iterative predictive experiment. We find that forecasts generated with the evolved indicators outperform those obtained with time series models.

Perspectives

These results show the potential of the methodology as a predictive tool. Furthermore, the proposed indicators are easy to implement and help to monitor the evolution of the economy, both from the demand and supply sides.

Oscar Claveria
AQR-IREA, Univeristy of Barcelona

Read the Original

This page is a summary of: Economic forecasting with evolved confidence indicators, Economic Modelling, September 2020, Elsevier, DOI: 10.1016/j.econmod.2020.09.015.
You can read the full text:

Read

Resources

Contributors

The following have contributed to this page