What is the difference between supervised and unsupervised learning?

Supervised learning uses labeled examples

In supervised learning each training example comes with a known answer, called a label. The model learns to map inputs to those labels. A market example would be learning to classify whether a condition was followed by an up or down move, using labeled historical cases.

The catch is that labeling future returns is noisy. The same pattern can be followed by both outcomes, so the model learns a blurry boundary at best. This is why supervised market models rarely produce sharp, dependable answers.

Unsupervised learning finds structure without labels

Unsupervised learning looks for structure in data that has no answers attached, such as grouping instruments that move together, or reducing many correlated indicators to a few underlying factors. It describes the data rather than predicting an outcome.

This family is often more honest in markets because it makes fewer promises. It organizes information instead of claiming to forecast it.

Where reinforcement learning fits

A third family, reinforcement learning, trains an agent to take actions and learn from rewards. It appears in research on execution and strategy, but it is extremely sensitive to the simulated environment and can learn to exploit flaws in the simulation rather than anything real.

This article is general educational information only. It is not financial, investment, or trading advice, and not a recommendation to buy or sell any instrument. Markets carry risk of loss, and past performance does not guarantee future results. Consult a qualified, licensed professional before making any decision.