|
The modelling of economic phenomena has for many years been in the centre of
interest of researchers, both from the perspective of economic sciences and from the
point of view of management processes. The development of such models makes it
possible, on the one hand, to forecast the development of specific phenomena, but
also to assess the effects of various economic decisions, including the evaluation of
their social consequences, the identification of potential risks, or the optimisation
of resource utilisation. On the other hand, in a great many cases classical statistical
methods, such as regression analysis or structural equation modelling, did not make
it possible to identify reliable and credible models linking current events in the
economy and their potential effects. The consequence of the multiplicity of possible
influencing factors, the various, usually non-linear mechanisms of their influence,
or their multidimensional interactions, was to obtain models with limited fit, which
did not reflect the nature of the relationship under study very well, nor did they have
much predictive power.
Artificial neural networks (ANN) are a solution for generating models with bet-
ter properties, capable of modelling complex relationships, taking into account the
different nature of the data, as well as having clear capabilities for predicting future
states. The article evaluates the possibility of applying an approach based on artificial
neural networks using a radial basis function (RBF) as an activation function to the
construction of an exemplary economic model representing the relationship between
the efficiency of the customs system and the economic security of the state, in this
case Ukraine, developed on official statistical data.
The analysis carried out proved that a model based on an artificial neural network
makes it possible to accurately predict the development of the economic phenomenon
under study. This makes it possible, on the one hand, to simulate its reaction to chang-
ing environmental conditions and, on the other, to potentially assess the significance
of the impact of individual input variables on its shape and intensity. The results
obtained therefore clearly indicate the possibility of using artificial neural networks
to build economic models, and are also a premise for replacing classical modelling
methods with methods based on such networks.
|
