Predicting Gold and Silver Price Direction Using Tree-Based Classifiers

Gold is often used by investors as a hedge against inflation or adverse economic times. Consequently, it important for to have accurate forecasts of gold prices. This paper uses several machine learning tree-based classifiers (bagging, stochastic gradient boosting, random forests) predict the price direction and silver exchange traded funds. Decision tree bagging, forests predictions are much more than those obtained from logit models. For 20-day forecast horizon, produce accuracy rates between 85% 90% while models 55% 60%. Stochastic boosting few percentage points less that horizons over 10 days. looking prices, bagging offer an attractive combination ease estimation. each silver, portfolio based on outperformed buy hold portfolio.