The 10 types of clustering that all data scientists need to know....
Matt Dancho (Business Science)@mdancho84
36 views
May 14, 2025
~2 min read
Advertisement
1
The 10 types of clustering that all data scientists need to know.
Let's dive in:
Let's dive in:
2
1. K-Means Clustering:
This is a centroid-based algorithm, where the goal is to minimize the sum of distances between points and their respective cluster centroid.
This is a centroid-based algorithm, where the goal is to minimize the sum of distances between points and their respective cluster centroid.
3
2. Hierarchical Clustering:
This method creates a tree of clusters. It is subdivided into Agglomerative (bottom-up approach) and Divisive (top-down approach).
This method creates a tree of clusters. It is subdivided into Agglomerative (bottom-up approach) and Divisive (top-down approach).
4
3. DBSCAN (Density-Based Spatial Clustering of Applications with Noise):
This algorithm defines clusters as areas of high density separated by areas of low density.
This algorithm defines clusters as areas of high density separated by areas of low density.
5
4. Mean Shift Clustering:
It is a centroid-based algorithm, which updates candidates for centroids to be the mean of points within a given region.
It is a centroid-based algorithm, which updates candidates for centroids to be the mean of points within a given region.
6
5. Gaussian Mixture Models (GMM):
This method uses a probabilistic model to represent the presence of subpopulations within an overall population without requiring to assign each data point to a cluster.
This method uses a probabilistic model to represent the presence of subpopulations within an overall population without requiring to assign each data point to a cluster.
7
6. Spectral Clustering:
It uses the eigenvalues of a similarity matrix to reduce dimensionality before applying a clustering algorithm, typically K-means.
It uses the eigenvalues of a similarity matrix to reduce dimensionality before applying a clustering algorithm, typically K-means.
8
7. OPTICS (Ordering Points To Identify the Clustering Structure):
Similar to DBSCAN, but creates a reachability plot to determine clustering structure.
Similar to DBSCAN, but creates a reachability plot to determine clustering structure.
9
8. Affinity Propagation:
It sends messages between pairs of samples until a set of exemplars and corresponding clusters gradually emerges.
It sends messages between pairs of samples until a set of exemplars and corresponding clusters gradually emerges.
10
9. BIRCH (Balanced Iterative Reducing and Clustering using Hierarchies):
Designed for large datasets, it incrementally and dynamically clusters incoming multi-dimensional metric data points.
Designed for large datasets, it incrementally and dynamically clusters incoming multi-dimensional metric data points.
11
10. CURE (Clustering Using Representatives):
It identifies clusters by shrinking each cluster to a certain number of representative points rather than the centroid.
It identifies clusters by shrinking each cluster to a certain number of representative points rather than the centroid.
12
EVERY DATA SCIENTIST NEEDS TO LEARN AI IN 2025.
99% of data scientists are overlooking AI.
I want to help.
99% of data scientists are overlooking AI.
I want to help.
13
On Wednesday, May 21st, I'm sharing one of my best AI Projects: Customer Segmentation Agent with AI
Register here (500 seats): learn.business-science.io/ai-register
Register here (500 seats): learn.business-science.io/ai-register
14
P.S. Want live AI + Data Science training with me for free?
Register for my next live AI for Data Scientists Workshop here: learn.business-science.io/ai-register
Register for my next live AI for Data Scientists Workshop here: learn.business-science.io/ai-register