Optimization of Backpropagation Using Harmony Search for Gold Price Forecasting

Gold is a precious metal often used for investment, due to its cash-in ease and yearly value increase. This indicates that price forecasting determine the prospect of future gold prices. Strong highly desired by investors make decisions. That why technical indicators are very important forecasting. By using information obtained can be more informative than pure One commonly methods Backpropagation (BP). BP has been shown have good performance in dealing with nonlinear problems. However, random determination parameters neurons hidden layer requires number get optimal results. Therefore, this study aims analyze optimization (BP) through Harmony Search (HS) algorithm evaluating use relevant In HS-BP model, method input variables layer. HS principle musicians aim finding best harmony. technique based on results fitness function. research, function Mean Square Error (MSE). optimize such way system provides lowest MSE improves Based Moving Average, Relative Strength Index, Bollinger Bands. Next, selected applied algorithm. Where implementation uses closing data January 2020-2021. The showed proposed better accuracy convergence error. level regular model.