CSCI 3950 Course Syllabus

Data Mining

Spring 2018


Name:              Dr.  Yao
Office:             Atkinson Hall 317
Telephone:      (478) 445-5483
 Office Hours: 8:20A.M.-9:20A.M. and 10:50P.M.-12:20P.M. on Tu and Th

         Emails that are not urgent only will be answered during the office hours



Principles of Data Mining, By Max Bramer, 3rd Ed, ISBN:   9781447173069

Data Mining: Practical Machine Learning, By WITTEN, 4th Ed, ISBN:   9780128042915



PREREQUISITES: C or above in CSCI2350/CSCI 3410 and with the professor's approval


  Classroom: Atk310

  Lab:  A&S143

An introduction to basic data mining skills, apply the skills in machine learning, and big data mining.

Regular attendance along with the timely completion of all homework assignments is essential for the successful completion of the course.  An unexcused absence from a test will result in a numerical grade of 0 for that test.

The grade for the course will be determined from two mid-term exams, presentation and homework assignments.  Relative weights along with tentative examination dates are as follows:

Exam I 30% (March 1, 2018)
Exam II                   30% (April 19, 2018)

Term Project             30%

Presentation      10% (May 3, 2018, 02:00P.M.-03:15P.M.)

Students are expected to present a true and honest representation of all academic work regarding their performance during the course. Unless specifically stated as part of an assignment, team/group efforts on assignments are prohibited. Students may discuss general approaches to solving problems related to an assignment, but must work on assignments individually.


WEEK              TOPICS


1.      Introduction to Data Mining; Data for Data Mining

2.      Introduction to Classification: Nave Bayes and Nearest Neighbor

3.      Using Decision Trees for Classification

4.      Decision Tree Induction: Using Entropy for Attribute Selection

5.      Decision Tree Induction: Using Frequency Tables for Attribute Selection

6.      Estimating the Predictive Accuracy of a Classifier

7.      Continuous Attributes

8.      Avoiding Overfitting of Decision Trees; More About Entropy

9.      Inducing Modular Rules for Classification

10.  Measuring the Performance of a Classifier

11.  Dealing with Large Volumes of Data

12.  Ensemble Classification; Comparing Classifiers

13.  Association Rule Mining I, II

14.  Association Rule Mining III: Frequent Pattern Trees

15.  Clustering

16.  Text Mining


         Martin Luther King Day: Jan. 15, 2018

         March 9, 2018 (5 P.M.) is the last day to drop without academic penalty (Unless if maximum number of dropped courses has been exceeded)

         Spring Break: March 19-23, 2018

         Last Day of Classes: May 7, 2018



The intellectual property of class assignments and other materials developed using university resources that are commercialized are reviewed under the USG and GC policies to determine ownership and/or payment rights. USG policies can be found at and GC policies can be found at


If you have a disability as described by the Americans with Disabilities Act (ADA) and the Rehabilitation Act of 1973, Section 504, you may be eligible to receive accommodations to assist in programmatic and physical accessibility. Disability Services, a unit of the GCSU Office of Institutional Equity and Diversity, can assist you in formulating a reasonable accommodation plan and in providing support in developing appropriate accommodations to ensure equal access to all GCSU programs and facilities. Course requirements will not be waived, but accommodations may assist you in meeting the requirements. For documentation requirements and for additional information, we recommend that you contact Disability Services located in Maxwell Student Union at 478-445-5931 or 478-445-4233.


Given the technological sophistication of Georgia College students, the student opinion survey is being delivered through an online process. Your constructive feedback plays an indispensable role in shaping quality education at Georgia College. All responses are completely confidential and your name is not stored with your responses in any way. In addition, instructors will not see any results of the opinion survey until after final grades are submitted to the University. An invitation to complete the online opinion survey is distributed to students near the end of the semester. Your participation in this very important process is greatly appreciated.


Fire drills will be conducted annually. In the event of a fire alarm, students will exit the building in a quick and orderly manner through the nearest hallway exit. Learn the floor plan and exits of the building. Do not use elevators. If you encounter heavy smoke, crawl on the floor so as to gain fresh air. Assist disabled persons and others if possible without endangering your own life. Assemble for a head count on the front lawn of main campus or other designated assembly area.


Students are permitted to miss class in observance of religious holidays and other activities observed by a religious group of which the student is a member without academic penalty. Exercising of ones rights under this policy is subject to the GC Honor Code. Students who miss class in observance of a religious holiday or event are required to make up the coursework missed as a result from the absence. The nature of the make-up assignments and the deadline for completion of such assignments are at the sole discretion of the instructor. Providing verifiable proof of the religious affiliation and activities are at the sole discretion of the instructor as well. Failure to follow the prescribed procedures voids all student rights under this policy.