A machine learning approach using labeled data to train models. In supervised learning, each input has a known output (label), and the model learns to map inputs to outputs. Examples include classification and regression. In forex robots, supervised learning is used for predictive tasks: e.g., a model might be trained on past price features (inputs) labeled by the next-period price change (output), learning to predict future movement. The model’s accuracy is evaluated on a separate validation set. Decision trees, neural networks and support vector machines are common supervised methods in trading, as they learn directly from historical labeled market data.