Although rigorous econometric methods have been used to build an abundance of macroeconomic models, there still exists a debate on the appropriateness of these models in representing the dynamic of the economy (Karakitsos, 1992; Moody, 1995). In time series and macroeconomic modeling, there are many assumptions being imposed on the behavior and functional relationship of the underlying variables (Cromwell et al., 1994). In addition, one may face with the complexity in the estimation of these models (Mills, 1990).
Nguyen, Dat-Dao, "Forecasting Macroeconomic Models with Artificial Neural Networks: An Empirical Investigation into the Foundation for an Intelligent Forecasting System" (1998). AMCIS 1998 Proceedings. 420.