Spring 2014: Data Mining [CS484]

General Description and Preliminary List of Topics

Data mining is the process of automatically discovering useful information in large data repositories. The course covers key concepts and algorithms at the core of data mining.

Topics include: classification, clustering, association analysis, anomaly detection.

Outcomes

  1. The ability to apply computing principles, probability and statistics relevant to the data mining discipline to analyze data.
  2. A thorough understanding of model programming with data mining tools, algorithms for estimation, prediction, and pattern discovery.
  3. The ability to analyze a problem, identifying and defining the computing requirements appropriate to its solution: data collection and preparation, functional requirements, selection of models and prediction algorithms, software, and performance evaluation.
  4. The ability to understand performance metrics used in the data mining field to interpret the results of applying an algorithm or model, to compare methods and to reach conclusions about data.
  5. The ability to communicate effectively to an audience the steps and results followed in solving a data mining problem (through a term project).

Grading

Assignments: 15%
Midterm: 25%
Final: 25%
Project: 30%
Participation: 5%

Exams are closed book. Assignments must be performed individually. Group work is NOT allowed, unless otherwise stated by the instructor. Any deviation from this policy will be considered a violation of the GMU Honor Code In addition, the CS department has its own Honor Code policies. Any deviation from this is also considered an Honor Code violation.