Artificial Neural Network Model for Predicting Exchange Rate in Ghana: A Case of GHS/USD

In today's global economy, accuracy in predicting the foreign exchange rate or at least trend correctly is of crucial importance for any future investment and this mostly achieved by use computational intelligence-based techniques as explored paper. The aim study was to develop an Artificial Neural Network (ANN) Model GHS/USD with inflation, nominal growth, monetary policy, interest rate, trade balance, gross international reserve, currency deposit, broad money major indicators Exchange rate. Three different ANN models which are Back Propagation (BPNN), Radial Basis Function (RBFNN) Generalized Regression (GRNN) were developed results measured Performance Index (PI), Mean Absolute Error (MAE), Root Square (RMSE) Percentage (MAPE). After extensive training, validation testing data, BPNN model seen be adequate MAE 0.28973, RMSE 0.32274, PI 0.10416 MAPE 7% a prediction (R2) 0.8460 against RBFNN have 0.37265, 0.48472, 0.2349, 8.52% R2 0.3744, GRNN 1.06482, 1.15444, 1.33274, 24.07% 0.2987.