What is it about?

The main objective of the paper is to generate mathematical functional forms that combine survey expectations about a wide range of economic variables to approximate the evolution of economic growth. We propose an empirical modelling approach based on genetic programming to forecast economic growth. First, we use evolutionary algorithms to estimate a symbolic regression that links survey-based expectations to a quantitative variable used as a yardstick. This allows us to derive mathematical functional forms that approximate the target variable. This set of empirically-generated proxies of economic growth are used as building blocks to forecast the evolution of GDP. Second, we use these estimates of GDP to assess the impact of the 2008 financial crisis on the accuracy of agents’ expectations about the evolution of the economic activity in four Scandinavian economies: Denmark, Finland, Norway and Sweden.

Featured Image

Why is it important?

The study applies a novel empirical modelling approach based on genetic programming to forecast economic growth using agents' expectations about the economic situation. We find an improvement in the capacity of agents’ to anticipate economic growth after the 2008 financial crisis. Notwithstanding, the predictive accuracy worsens in relation to the period prior to the crisis. The most accurate GDP forecasts are obtained for Sweden.

Perspectives

By means of algorithms inspired by biological evolution, evolutionary computation can produce highly optimized solutions in a wide range of problem settings. In this study we show its potential for generating mathematical functional forms that combine expectations about a wide range of economic variables to approximate the evolution of economic growth.

Oscar Claveria
AQR-IREA, Univeristy of Barcelona

Read the Original

This page is a summary of: Evolutionary Computation for Macroeconomic Forecasting, Computational Economics, November 2017, Springer Science + Business Media, DOI: 10.1007/s10614-017-9767-4.
You can read the full text:

Read

Resources

Contributors

The following have contributed to this page