Authors test the suggested model on high-frequency time series data of USD/CAD and examine the ability to forecast exchange rate values for the horizon of one day.
To determine the forecasting efficiency, they perform a comparative statistical out-of-sample analysis of the tested model with autoregressive models and the standard neural network.
They also incorporate genetic algorithm as an optimizing technique for adapting parameters of ANN which is then compared with standard backpropagation and backpropagation combined with K-means clustering algorithm.
Individual traders comprise a very small part of this market.
Because of the volatility in the price of foreign currency, losses can accrue very rapidly, wiping out an investor’s down payment in short order.
Any company operating globally must deal in foreign currencies.
It has to pay suppliers in other countries with a currency different from its home country’s currency.
This is the exchange rate (expressed as dollars per euro) times the relative price of the two currencies in terms of their ability to purchase units of the market basket (euros per goods unit divided by dollars per goods unit).