Gold Price Prediction Using Machine Learning Algorithms

Gold has historically been one of the most valuable assets, widely used in trade, investment, and as a store of wealth. Countries with substantial gold reserves are often perceived as economically strong, as gold holdings serve as an indicator of financial stability. Apart from nations, individual investors and corporations also see gold as a safe investment option, especially during times of economic instability. The price of gold is highly volatile, influenced by several global factors, such as inflation, interest rates, currency exchange rates, stock market performance, and geopolitical events. Due to the unpredictability of goldprices, forecasting its future trends is a significant challenge for investors and financial analysts. Various studies have attempted to establish relationships between economic factors and gold prices, using statistical and machine learning approaches. This study, titled "Gold Price Prediction," applies machine learning techniques to analyze historical data and predict future gold prices. The study implements supervised learning models, including Linear Regression, Random Forest Regressor, and Gradient Boosting, to develop a predictive framework. The dataset used in this study spans ten years (2008–2018) and includes financial indicators such as silver prices, stock exchange profits, USD exchange rates, and US oil ETF prices. The models are trained and tested using historical data, and their performance is evaluated using accuracy metrics such as Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R² score. Among the algorithms tested, Random Forest Regressor achieved the highest accuracy and lowest error rates, making it the most effective model for gold price prediction.