| By: |
Marek Hlavacek;
Michael Konak;
Josef Cada |
| Abstract: |
One of the most significant factors influencing the liquidity of the financial
market is the amount of currency in circulation. Although the central bank is
responsible for the distribution of the currency it cannot assess the demand
for the currency, as that demand is influenced by the non-banking sector.
Therefore, the amount of currency in circulation has to be forecasted. This
paper introduces a feedforward structured neural network model and discusses
its applicability to the forecasting of currency in circulation. The
forecasting performance of the new neural network model is compared with an
ARIMA model. The results indicate that the performance of the neural network
model is better and that both models might be applied at least as supportive
tools for liquidity forecasting. |
| Keywords: |
Neural network, seasonal time series, currency in circulation. |
| JEL: |
C45 C53 |
| Date: |
2005–12 |
| URL: |
http://d.repec.org/n?u=RePEc:cnb:wpaper:2005/11&r=ict |