STAT 492/592: Data Mining

SNP0026 MWF 1:00-1:50 pm

Grading:

• 30% Homework assignments
• 50% Projects: presentation & report
• 20% Class participation including presentation

Instructor: Xijin Ge Tel. 688-6879 Email Xijin.Ge@sdstate.edu

Office hours: by appointment Harding Hall 124

Textbook:

Data Mining: a knowledge Discovery Approach by K. J. Cios, W. Pedrycz, R. W. Swiniarski & L. A. Kurgan, Springer, 2007. ISBN-13: 978-0-387-33333-5

Required Software:

Student will be required to obtain SAS Enterprise Miner via SAS onDemand ($50).

Course Description:

This course is an introduction to data mining for students in mathematics, computer science and related fields. Some of the topics will cover data mining in financial applications. Homework may involve some programming.

Topics covered:

1. Data mining: definition, history, & applications

2. Data collection, quality control, pre-processing, and warehousing

3. Data visualization methods

4. Dimensionality reduction methods

5. Clustering analysis methods

6. Predictive classification algorithms

7. Text mining & natural language processing

8. Performance evaluation metrics

Attendance: While attendance is not a formal part of the course grade, there will be material presented in the class that is not in the book, so regular attendance is important. If you need to miss a class meeting, you are responsible for getting the material covered during that class meeting and for submitting any homework that was due during that class meeting.

Homework will be required to be sent to the instructor via digital drop box in D2L by the designated due date. In exceptional cases when delay is anticipated, please email the instructor before the due date. Without acceptable excuses, students can only get 50% of the total point on the homework if turned in late but within two weeks.

Communications/discussions with other students via D2L are required and are part for grading. A minimum of one post per week on the discussion board is expected for online students.

Projects: Students will carry out several group projects to analyze real data in the course. As our final project, students will be participating in the M2009 data mining contest (http://www.sas.com/events/dmconf/contest.html). We will invite several experts in different fields (financial, climate, etc) as guest lectures.

Attendance: For students registered for on-campus section, attendance is not a formal part of the course grade, but is strongly encouraged. For students in the online section, attendance is not expected. However, students should log-in to the course via D2L and check regularly for class materials, homeworks, etc.

Academic Freedom and Responsibility Statement Freedom in learning. Students are responsible for learning the content of any course of study in which they are enrolled. Under Board of Regents and University policy, student academic performance shall be evaluated solely on an academic basis and students should be free to take reasoned exception to the data or views offered in any course of study. Students who believe that an academic evaluation is unrelated to academic standards but is related instead to judgment of their personal opinion or conduct should first contact the instructor of the course. If the student remains unsatisfied, the student may contact the department head and/or dean of the college which offers the class to initiate a review of the evaluation.

Student with Disability: Contact SDSU Disability Service at 688-4504 (Coordinator Nancy Hartenhoff-Crooks email: Nancy.Crooks@sdstate.edu ) if you anticipate needing any type of accommodation in order to participate in this class.

ACADEMIC DISHONESTY STATEMENT

Academic Dishonesty will not be tolerated. Plagiarism, copying or cheating will result in no credit for that assignment. Severs or repeated offenses will result in further disciplinary action such as the reduction of the final grade and formal reporting of the incident to the student conduct committee.

Grading: Maintaining a score for the semester of 90-100, 80-89, 70-79, 60-69 will assure the grade of A, B, C, and D, respectively. However, attendance and class participation, etc, could be used to adjust borderline cases when course grades are assigned.