Course Description

Data mining is the process of finding useful patterns in data. The objective of data mining is to use discovered patterns to help explain current behavior or to predict future outcomes.

This course will explore some data mining methods with a primary focus on model building and testing, as well as on interpreting and validating results. Model building is both an art and a science that is best understood from the perspective of learning by doing and this course will supplement the text with exercises with a data mining tool that will enable the student to experimentally build and test data mining models.

Course Objectives

After completing CSIS 5420 - Data Mining students should be able to:

• Explain what data mining is and how data mining can be employed to solve real problems.
• Recognize whether a data mining solution is a feasible alternative for a specific problem.
• Step through the knowledge discovery process and write a report about the results of a data mining session.
• Apply basic statistical and non statistical techniques to evaluate the results of a data mining session.
• Recognize several data mining strategies and know when each strategy is appropriate.
• Explain how several data mining techniques build models to solve problems.
• Summarize the structure of a data warehouse and how a data warehouse can be used to enhance business opportunities.
• Describe what on-line analytic processing (OLAP) is and how it can be applied to analyze data.
• Explain how expert systems represent general models that emulate human actions.
• Use a goal tree to help design a rule-based system.
• Recognize that intelligent agents are computer programs able to assist us with everyday tasks.
• Describe the types of problems that can be solved by combining an expert systems problem-solving approach and a data mining strategy.
• Apply the software that accompanies the text to solve real problems.

Incoming Competency

Basic knowledge of computer and information technology and completion of CSIC 5410 - Introduction to Data Mining.

Textbook

Data Mining, A Tutorial-Based Primer (with CD) (2003). Richard J. Roiger and Michael W. Geatz, Pearson Education, Inc., ISBN 0-201-74128-8.

Online Participation Requirement

• Students will be expected to participate on-line three or more times per week, and will be graded on their consistent on-line participation. On-line participation counts for 25% of a student's final grade.
  
  Furthermore, it is the both quality (ideas and insights) and the quantity (number of postings) of your postings that determine your grade. Discussion areas will remain open for the entire week for you to return and refer to. However, there will be new questions for discussion each week. Do not wait until the last minute to get into the discussion; check in several times a week.

• Keep in mind the following for getting the most out of our discussions:
  • Ask questions of others
  • Respond to others' questions and comments
  • When responding, identify the person and topic to which you are responding
  • Submit comments that demonstrate insights about the topic or link it other areas of our class discussion and learning
  • Share insights gained through your experiences and other course work

Assignment Submission

You are required to submit all assignments in a timely manner via WebCT Assignments area. WebCT will stamp your submission date/time automatically. Please be aware that all assignments in this course use Eastern Time.

If you encounter technical problems in WebCT submission, please contact the

• Collegis Help Desk at (877) 725-4357 (toll-free to US residents only) or

Via e-mail at http://eduprise.custhelp.com

In the event of technical problems it is a good idea to contact your instructor right away and submit your assignments to your instructor's secondary e-mail account if necessary. Your instructor's secondary e-mail address can be found in "instructor introduction" section.

Assignments

There will be seven assignments during the course. However, all together, the assignments represent only 15% of the grade for the course. The weighting on the assignments reflects their purpose:

• The assignments will help you assess your understanding of the material.
• The assignments will help you keep up with the reading and activities in the course.
• The assignments will help you prepare for the midterm and the final exam.

The assignments will occur on weeks 1, 2, 3, 4 ,6, 7 & 8. In other words, no assignment in the weeks with exams (5 & 9). All assignments will be short essay questions. This will allow you to clearly communicate your understanding of the course material. Please use Microsoft Word to answer the assignments and then submit your document using the WebCT upload process.

The two exams will also be short essay questions. I believe that this format helps me assess your understanding of the course material better than true/false or multiple choice questions. Please use Microsoft Word to answer the exam questions and then submit your document using the WebCT upload process.

Virtual Office Hour - Online Chat

Chat may be used for holding virtual office hours. If you are interested in this feature please let the instructor know in advance. For example instructors may schedule chat sessions the week before midterm and final exams to answer questions you may have for the course. The date and time for chatting will be posted in Discussions area.

Grading Policy

Grade Scale:

A	93 - 100%
A-	90 - 92 %
B+	87 - 89 %
B	83 - 86 %
B-	80 - 82 %
C	70 - 79 %
F	below 70 %

Accommodations

If you have a disability that may have some impact on your work in this class and for which you may require accommodations, please contact me or the Director of the Academic Resource Center, so that such accommodations may be arranged.

Policy Statements

• All work is due before the beginning of the next week's class session and becomes the property of the department. Any work turned after that will be considered late and the grade will be reduced by 10 percent.
• For graduate courses, the last day to drop the course with a full refund is Friday of Week 2.
• For graduate courses, the last day to withdraw from the course, without a refund, is Friday of Week 6.
• Avoiding plagiarism. Any student caught cheating or committing plagiarism might fail the class and be subject to further disciplinary action. Always restate ideas in your own style and give credit to your sources. Click this link for help on paraphrasing.
• This syllabus may be revised at the discretion of the instructor without the prior notification or consent of the student.

This syllabus is subject to change!