Chevron Left
Back to Cluster Analysis in Data Mining

Cluster Analysis in Data Mining, University of Illinois at Urbana-Champaign

4.3
150 ratings
32 reviews

About this Course

Discover the basic concepts of cluster analysis, and then study a set of typical clustering methodologies, algorithms, and applications. This includes partitioning methods such as k-means, hierarchical methods such as BIRCH, and density-based methods such as DBSCAN/OPTICS. Moreover, learn methods for clustering validation and evaluation of clustering quality. Finally, see examples of cluster analysis in applications....

Top reviews

By DD

Sep 25, 2017

A very good course, it gives me a general idea of how clustering algorithm work.

By TK

Oct 10, 2017

Very intense and required complex thinking and programming skill

Filter by:

32 Reviews

By Ian Wang

Aug 20, 2018

Nice lecture.

The programming assignment is difficult, more instructions could be provided.

By barbara

Aug 01, 2018

This course is a great resource to learn about the different clustering algorithms out there. I need to solve a clustering problem in my research and my knowledge about clustering ended at kmeans. The course teaches systematic ways to find out whether you should be clustering your data in the first place, what clustering algorithm should be best for your data, and how to evaluate the goodness of the algorithm and the used parameters. Many unknown unknowns have been illuminated to me by the course.

By Steve Sekowski

Jul 18, 2018

I feel like the programming assignments could've been more involved/tied to the clustering algorithms themselves, rather than just submitting a text file with results (e.g., maybe solve a practical problem with an algorithm of choice). Quizzes sometimes contained ambiguous and/or poorly-written questions/answers. Some of the later lectures simply featured equations on a powerpoint and did not involve any examples on how to use them.

By Srinath Ramchandra Mitragotri

Jul 10, 2018

Gave a very good understanding of cluster analysis - explaining all different methods and algorithms, the benefits and drawbacks of each. The tool ClusterEng looks very good and can help in a lot of situations. Thank so much

By GANG LI

Jan 26, 2018

This is a very good course covering all area of clustering. The only thing I feel a little struggle is some algorithm explained too brief, I prefer some detail step by step examples.

By zshowing

Dec 25, 2017

The instructor basically reads the slides line by line, with very few examples.

By ADARSHPANDEY

Dec 24, 2017

Course is very good I learnt about a lot of things related to clustering. Actually it is a very good introductory course in clustering compared to the resources available online in general. Although few things that I think might help improve the course

i) Course only implements K-Means which is a very simple algorithm, instead of this or in addition to this implementation of few advanced algorithms like DBSCAN or CHAMELEON should be added.

ii) A no. of times prof only seems to be reading the slides which make things a little bit unclear i.e, the sentences used should be more common or explanatory rather than just reading the slides which the student itself can.

Apart from these things I truly enjoyed and learned many new things.

Thank you everyone involved in developing this course

By Vasco De Sá Nunes Correia Diogo

Nov 22, 2017

Excellent overview of many clustering algorithms!

By Alexandre Miranda Bastos

Nov 11, 2017

My analysis is that the assessments do not match the depth of what is explained.

By Bernd

Oct 27, 2017

Great course that provides a good overview of different clustering approaches and how to deploy them to various problems. I found the lecture material unclear or vague at times, so that for certain topics understanding heavily depends on one diving through the provided reading material (which I found very helpful). However, the topic of evaluation is very dense in the lectures and the provided book chapters do not provide relevant insights as well, making the programming assignment for this part quite challenging (at least if not already deeply familiar already with the concepts involved). Be ready to invest effort to make the most of this.