A real time leading economic indicator based on text mining for the Spanish economy. Fractional cointegration VAR and Continuous Wavelet Transform analysis.

Abstract

The main aim of this paper is to build a Real Time Leading Economic Indicator (RT-LEI) that improves Composite Leading Indicators (CLI)’s performance to anticipate GDP trends and turning points for the Spanish economy. The indicator has been constructed using a Factor Analysis and is composed of 21 variables concerning motor vehicle activity, financial activity, real estate activity, economic sentiment, and industrial sector. The data sources used are Google Trends and Thomson Reuters Eikon-Datastream. This work contributes to the literature, studying the dynamics of GDP, CLI and RT-LEI using Fractional Cointegration VAR (FCVAR model) and Continuous Wavelet Transform (CWT) for its resolution. The results show that the model does not present mean reversion and it is expected the RT-LEI reveals a bear trend in the next two years, alike IMF and Consensus FUNCAS′ forecasts. The reasons are mostly associated with escalating global protectionism, uncertainty related to Catalonia and faster monetary policy normalization.