CS 5973 Knowledge Discovery (and Data Mining)

In today's information-rich world, finding automatic ways to sift through the wealth of information and to identify the salient patterns is critical. This course will cover knowledge discovery approaches to addressing this issue. By the end of the semester, students will be able to:

• Recognize a knowledge discovery task
• Choose an appropriate knowledge representation (static vs dynamic, discrete vs continuous, propositional vs relational)
• Identify the elements of a successful knowledge discovery algorithm
• Apply current knowledge discovery algorithms to new situations
• Create new and successful knowledge discovery algorithms
• Evaluate and analyze the performance of new approaches

This will be a seminar style class where we will read both the book and discuss current papers. In addition, we will have a class-wide project (most likely on the new netflix data where we will aim to improve the prediction of movies that people will enjoy) that we will work on and discuss.

Please note that most of the course material will go on Desire2Learn.

• Course syllabus (as of 1/17/07)
• Course schedule (updated as semester progresses)