The exchange rates and gold rates play a vital role in controlling the dynamics of the world market. As a result, the appropriate prediction of both of them is a crucial factor for the success of many businesses and fund managers. Artificial Neural Network (ANN) is a modern non -linear technique used for prediction that involves learning and pattern recognition. The historical monthly data from Jan 2011 to Dec 2020 (10 years) for five exchange rates namely US Dollar (USD), Great Britain Pound (GBP), Kuwaiti Dinar (KWD), Japanese Yen (JPY), and Hong Kong Dollar (HKD) and the average monthly gold rates from the June 2011 to Sept 2020 (10 years) were modeled using this technique and the Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Percentage Error (MAPE) are used to evaluate the accuracy of the models.