Class time

May 12 - August 9, 2021

Instructor and TAs

About this course

As a data scientist, what should you do when you are facing a huge amount of complicated data from real life applications? This course introduces the core techniques in big data analytics, namely knowledge discovery in databases (KDD), also known as data mining (DM). It focuses on the principles, essential ideas, fundamental algorithms, implementations, and applications.

Prerequisites

• Comprehensive understanding and fluent skills in data structures, such as linked data structures, B-trees, and hash functions.
• Analysis of algorithms and time complexity.
• Operating systems, main memory and disk management, file systems.
• Elementary probability theory and statistics, such as random variables, distributions, probability mass functions, sampling, and statistical tests.

Textbook and references

• (Official textbook) Data Mining: Concepts and Techniques (3rd ed.), Jiawei Han, Micheline Kamber, and Jian Pei, Morgan Kaufmann, 2011.
• Drafts of some chapters in the 4th ed. will be available for interested students.

Format and Zoom link

• A combination of live zoom meeting sessions and pre-recorded lectures. Students are required to attend the live sessions. See the schedule section for details.
• Live sessions of classes through zoom CMPT 459 zoom.
• Instructor’s office hours through zoom Jian’s office hour zoom.
• TAs’ office hours through zoom TAs’ office hour zoom.
• In-class exams.

Course outline

1. Welcome and introcution
2. Business intelligence (data warehousing, OLAP and data lakes)
3. Mining patterns and rules
4. Predictive analytics
5. Clustering analytics
6. Outlier detection

Assignments (tentative, subject to changes)

Schedule (tentative, subject to changes)