Clustering

Statistical Techniques in Tableau

Maarten Van den Broeck

Content Developer at DataCamp

Supervised vs. unsupervised machine learning

Supervised learning

Apply known relationship between variables on new, unseen data
E.g. regression, exponential smoothing

Unsupervised learning

Looks for similar data points and detects patterns
E.g. clustering

k-means clustering

Visual representation of the k-means clustering algorithm.

k-means clustering

Visual representation of the k-means clustering algorithm. Two random centers are selected.

k-means clustering

Visual representation of the k-means clustering algorithm. The closest points are assigned to those centers.

k-means clustering

Visual representation of the k-means clustering algorithm. The centers are moved to the new center.

k-means clustering

Visual representation of the k-means clustering algorithm. The process is iterative and repeats.

k-means clustering

Visual representation of the k-means clustering algorithm. The algorithm stops when the centers stop moving.

Assess clustering quality

Between-group sum of squares

Visual representation of k-means clustering. Between-group sum of squares is the sum of the squared distances between the centers and the mean of the whole dataset.

The higher, the better

Within-group sum of squares

Visual representation of k-means clustering. Within-group sum of squares is the sum of the squared distances between the centers and the points of the cluster.

The lower, the better

Let's practice!

Statistical Techniques in Tableau