**Unsupervised learning** is a machine learning technique that is used to find *previously unknown* patterns in data. Unsupervised learning algorithms use data without labeled outcomes to predict outcomes for unseen data.

# Types

## Clustering
**Clustering algorithms** process data to split data points into clusters. The idea is that data points with similar features should be assigned to the same cluster and that the points in different clusters should have different features. Some of the different clustering types include:

* K-means clustering
* Hierarchical clustering



## Association

**Association learning** involves finding relationships between features in a dataset. There are minimal thresholds imposed on significance levels to filter the *interesting* rules out of all the other association rules.  

## Pros and Cons

**Pro**

* Unlabelled data is often easier to obtain than labeled​ data as no one is required to understand *and then* label the data.

**Con**

* In K-means clustering, the user has to provide the number of clusters. This may not be easy to determine.

What is unsupervised learning?

Types

Clustering

Association

Pros and Cons