A type of supervised learning task where the model predicts discrete labels (e.g. “price up” vs “price down”) from input data. Classification models (like decision trees, neural nets) are trained on historical forex data labeled by past outcomes, then used to categorize new situations. For instance, a forex robot might use classification to decide whether to go long or short based on current market indicators. Common algorithms include decision trees, random forests, support vector machines, and logistic regression.

Back to Robots Glossary Index