Forecasting Spanish economic activity in times of COVID-19 by means of the RT-LEI and machine learning techniques

ABSTRACT

The main aim of this paper is to analyse and estimate the behaviour of the Spanish economic activity in the next 12 months, by means of a Real-Time Leading Economic Indicator (RT-LEI), based on Google Trends, and the real GDP. We apply methodologies based on fractional integration and cointegration to measure the degree of persistence and to examine the long-term relationship. Finally, we carry out a forecast using a Machine Learning model based on an Artificial Neural Network. Our results indicate that the Spanish economy will experience a contraction in 1Q-21 and will require strong measures to reverse the situation and recover the original trend.

KEYWORDS:

• Leading economic indicators
• business cycle
• fractional integration
• Google Trends
• machine learning

JEL:

• C22
• E32
• E37

Disclosure statement

No potential conflict of interest was reported by the author(s).