Predicting gold prices accurately is crucial for investors and policymakers alike, given gold's significance as a store of value and hedge against economic uncertainty. In this study, we propose a novel approach using Multilayer Perceptron (MLP) neural networks to forecast gold prices. Leveraging historical data on gold prices and relevant economic indicators, we trained an MLP neural network model. Our model achieved remarkable accuracy, with a prediction error for the test phase close to 0.001. This indicates the efficacy of MLP neural networks in capturing the complex relationships underlying gold price movements. Our research contributes to the growing body of literature on machine learning applications in financial forecasting and provides valuable insights for stakeholders in the gold market. Further exploration of this approach holds promise for enhancing gold price prediction models and informing investment decisions in the financial markets.