Clustering algorithms group data points into clusters based on similarity, without labeled outcomes. For example, k-means clustering partitions n observations into k clusters such that each point is assigned to the nearest cluster mean. In trading, clustering can identify regimes or patterns in market data (e.g. grouping days by volatility or trend) to inform strategy design. This unsupervised learning helps forex robots detect structure in market data (like clustering similar currency behavior) that might not be evident otherwise.

Back to Robots Glossary Index