May 21, 2014

Great Online Course for Data Mining!

Data mining appeal for companies and analytic practitioners is growing by the day. So where should you start with it? Recently I have been evaluating data mining software and courses and I came across a very good one that I can recommend without any hold-backs. This is the MOOC organized by University of Waikato. MOOC stands for "massive open online course" but do not be fooled by the name - its a serious course that delivers right on the target.


What is in?
The course has two parts - "Data Mining with WEKA" and "More Data Mining with WEKA". Both courses are structured in 5 classes and each class has six lessons followed by activities. Classes are designed to take one week each but the materials are available on the site till the end of the course.
Data Mining with WEKA covers working with the software, evaluation methods, classification and builds on the overall data mining process.
More Data Mining with WEKA covers the functionality  that was not covered in the first part, working with big data, discretization, clustering, classification and association rules, attribute selection, neural networks, costs and performance evaluation.
The lessons are about 10 min long and are narrated by Prof. Ian Witten. The immersion in the subject is gradual and covers lot of material from basics to best practices. The course is very practical - each concept is demonstrated with WEKA and the most important metrics and parameters are covered only without unnecessary details. There is no math in it that makes is suitable for larger audience. The students who want to go deeper could do that in the supplied reading materials. Chapters of Prof. Witten excellent book "Data Mining (3rd Edition)"are made available for them for free. Reading is not required for course completion and one can get everything from the lectures and activities. The activities are organic part of the course. They are interesting, though-provoking and build skills in a nice gradual manner.
Another thing I like is that all the course materials are available on the website. There is a nice and friendly forum where you could get help from other students or by Prof. Witten himself!

Who is it for?
The course is suitable for a large audience - students, practitioners who want to refresh their knowledge or learn how to use the software, students, researchers who want to harness the power of DM or anyone else who wants to expand her skills and knowledge. There are requirement for math or stat degrees and even humanitarians would do fine if do not want to go deeper.

How much time does it require?
You could expect to spend between 30 and 60min for each lesson and its activities if you do not go into reading the chapters.

When is it available?
The courses are run few times a year. Currently they are not opened for registration. Go to the website and subscribe for announcements for openings.


Will you get a certificate?
Yes, you can get one. There are two assessments in a class - a mid-term and post-course. Pass them with more than 70% success and a certificate will be delivered to your email.


What is WEKA?
WEKA is very powerful data mining software. Despite it is free, it has all the components to make it absolutely fit for industrial applications. Find more here.

There are many other data mining courses available online but for sure the unique combination of accessibility, quality, price, prerequisites, practicality and used software make this one a very good choice.

No comments:

Post a Comment