Gaining confidence in the revised consumer confidence indicator: nonlinear optimization approach

This study aims to methodologically improve the European consumer confidence indicator (CCI), one of the most closely observed economic indicators. Our models utilize nonlinear optimization targeting to maximize the number of correctly predicted directions of change in the annual final consumption growth rates. We also opt for a new weighting scheme as we believe the current one, applying equal weights for all the variables in CCI’s calculation, may be significantly improved. Indeed, the new weighting scheme shows that assessment of the past financial situation is not a relevant variable for correctly predicting the change in final consumption. Moreover, the results show that our model significantly improves the CCI’s ability to predict the direction of change in consumption growth rates in the EU. With the new weighting system, the new CCI’s average lead time appears much shorter. This finding is more realistic since the four-quarter lead time (associated with the official CCI) implies the indicator’s hardly plausible ability to announce macroeconomic trends a whole year in advance. We see an economic explanation for the shorter average lead time in the adverse experiences of the previous decade, which might have resulted in nowadays consumers’ careful reading of the market signals and greater reactivity to new economic conditions.