GBUS 738: Data Mining for Business Analytics Master Syllabus
Course Instructor:
Office Number:
Office Hours:
Email:
Course Meeting Times:
Course Website: Canvas
Course Introduction
Data mining—the art and science of extracting useful patterns from large pools of data—is of growing importance in today’s world. Today’s digitally enabled enterprises generate and capture huge amounts of data and are trying to harness this abundance to make better predictions, decisions, and strategies. Therefore, managers now need to know the fundamentals of data mining, its appropriate use, and its limitations. This course will provide an introduction to the data mining process and methods to enhance managerial decisionmaking. The students will learn to ask the right questions and draw inferences from the data by using appropriate data mining tools. The students will also acquire hands-on experience using data mining software. Overall, the course will enable students to approach business problems in a data-driven way, envision data mining opportunities in organizations, and also follow up in an evidence-based manner on ideas or opportunities that present themselves.
Course Objectives
This course focuses on analytical decision-making in uncertain and complex management scenarios using data mining and information systems. Students will learn to preprocess datasets, apply supervised and unsupervised learning methods for pattern extraction, and evaluate algorithmic results to propose actionable business solutions. Practical applications will emphasize the steps from goal definition to model deployment in real-world contexts.
Course goals are:
- Introduce the steps involved in data mining, from goal definition to model deployment.
- Use data preprocessing techniques to prepare datasets for analysis.
- Apply supervised learning methods, such as classification and prediction, to extract patterns in business data.
- Apply unsupervised learning methods, such as clustering, to extract patterns in business data.
- Evaluate and interpret results of data mining algorithms and propose business solutions based on them.
Content Delivery
This course uses the Canvas learning management system (LMS). Training on the main Canvas features is required for those who are new to the LMS. If you are not new to this LMS, you may also benefit from a refresher on the main features of Canvas.
All course materials, assignments, and announcements will be available on Canvas. It is recommended you subscribe to Canvas notifications. That way, announcements will also be delivered to your email. Make sure you check your email on a weekly basis. To ease the search in your mailbox, filter the emails by subject ‘GBUS738.’
Each class in this course consists of a combination of lectures, discussions, and hands-on data analytics sessions.
- At the beginning of each learning week, I will release the new learning module with the relevant materials. You are expected to have access to all weekly learning materials at the beginning of each class session, i.e., open links, open slides, and open software files.
- In the class session, we will follow the presentation outline and complete one of the course goals. Your active participation is expected. I intend to rely on your curiosity and questions when delivering the material.
- At the end of each class, I will release the preparation materials for the next week, typically in the form of articles or other content media. You are expected to get familiar with these materials before the next class. Before the first week of class, you are expected to complete one of such preps.
The Canvas weekly module structure will follow the same pattern.
Course Materials
(R) mark required materials
Textbook
- (R) Gordon S. Linoff, & Michael J. A. Berry (2011). Data Mining Techniques: For Marketing, Sales, and Customer Relationship Management. Third edition. ISBN: 978-1-118-08745-9. Coded as DMT in future course references.
- (R) Gareth James, Daniela Witten, Trevor Hastie, & Robert Tibshirani (2023). An Introduction to Statistical Learning with Applications in R. Second edition. Springer. Available under opensource license from: https://www.statlearning.com. Coded as ISLR in future course references.
- (R) Hadley Wickham, Mine Çetinkaya-Rundel, & Garrett Grolemund (2023). R for Data Science. Second edition. O’Reilly Media, Inc. Available under open-source license from: https://r4ds.hadley.nz. Coded as RDS in future course references.
Other Learning Materials
- (R) Articles and Cases. The course will use articles, videos, and cases to illustrate the concepts of data mining. All articles and cases for this course can be downloaded for free from the Internet or the George Mason library.
Attendance Policy
Class attendance and participation are required. You can miss 2 out of 8 (25%) class meetings without an explanation of the reason. If you are absent more than 2 times per semester, you need to provide advance notice, e.g., in case of a business trip or observance of a holiday, or doctor’s/court notice/police report, etc., in all other cases. Personal excuses will not be grounds for a reasonable excuse. Late attendance or early leave is the same as absence.
Treat the class sessions as near-real-world professional meetings. What’s in it for you? Learning materials are freely available on the Internet, and anyone can study them. The value of the class environment stems from interactions and the ability to receive feedback from your instructor and your peers. Receiving feedback on its actions and correcting behavior is how any neural network learns, and so is yours.
Satisfying class attendance entails:
- The instructor knows your face and name
- Your Zoom avatar is signed with your first and last name.
- Your Zoom avatar has your portrait profile picture.
- Your camera is turned on for the first 30 minutes of the class.
- Asking relevant questions in class
- You unmute yourself at least once per two classes and ask a question.
- Contributing to class discussion (both quantity and quality)
- You unmute yourself at least once per two classes and ask a question or respond to the stated question.
- You type additional comments in chat and comment on other students’ comments in a professional and respectful manner.
- Being knowledgeable about basic information contained in the cases
- You unmute yourself when the instructor or a classmate refers to you.
- You should expect to be called out for providing answers to class questions at times.
Grading and Assessment
Grade Distribution
| A/A- | >=90% |
| B+/B/B- | 75% to <90% |
| C | 60% to <75% |
| F | <60% |
Grading Scale
| Quizzes* (5) | 10% |
| Homework (3) | 20% |
| Course project | 30% |
| Final Exam | 35% |
| Class participation | 5% |
Comments on grading:
- Quizzes*: The best 5 of 6 quiz grades are counted towards the final course grade.
- Split between +/- letter grades will be determined by the instructor based on the clustering of scores.
- As the course is an elective, Costello policy dictates that the mean GPA will be 3.50 +/- 0.1.
All assignment submissions are due on Canvas.
Quizzes (10%)
There are 6 quizzes, one for each week of class beginning the second week of classes. The quizzes will test your knowledge of the previous class material. The quizzes may contain multiple-choice scenario-based questions as well as open-ended questions. The grading of each quiz is as follows:
- Answering four (4) or more questions correctly will result in 100% for the quiz.
- Zero correct answers or not taking the quiz before the deadline will result in a score of zero.
- Anything in between will result in a 60% score for the quiz.
The quiz with the lowest grade will be dropped, and the best 5 of 6 quiz grades are counted towards the final grade.
Individual Homework (20%):
There are three (3) individual homework assignments. Homework assignments will require you to work on data analytics problems in R software. The requirements for each assignment and the datasets will be posted on the course website. Although the submissions will be evaluated individually, you will be assigned to a study group with several of your classmates. The assignments can be discussed but not copied and pasted.
Course Project (30%)
The course projects are done in teams. The course project consists of three parts with respective deadlines. (1) The project proposal requires teams to identify the business problem that can be addressed with data analytics. The project proposal deliverable is due by the third week of the class. The team is required to meet with the instructor to receive feedback on their proposals in the fourth or fifth weeks of the class. (2) The project report requires teams to execute their plan outline in the first phase and incorporate corrections. The project report deliverable is due by the sixth week of the class. Project reports will be assigned for peer review. Peer review will not be counted for the final assignment assessment. (3) The project presentation requires teams to present their project goal, outcomes, and data analytics approaches. The project presentation deliverable is due by the last class. The teams will also be asked to deliver feedback on their team members’ collaboration and contribution. The purpose of the feedback is to ensure each team member’s involvement and not to allow free riding. Free riders will be assigned to deliver individual projects, and their assignment grades will be determined by the quality of their individual work.
Final Exam (35%)
There is an individual take-home exam that may include quiz- and homework-like questions. You will be given 48 hours to complete and turn in the final exam answers on Canvas. The final exam will be released on Friday of the last week of classes at 7 PM EST and due on Sunday of the last week of classes at 7 PM EST.
Class Participation and Professionalism (5%)
You will be expected to participate in class discussions and answer in-class questions. The class participation will be evaluated on a 3-level scale: ‘exceeding expectations,’ ‘satisfactory,’ and ‘not satisfactory.’ Some tips on how to get a satisfactory performance score are in the Attendance Policy section of this syllabus. The analytical depth and quality of the course project peer review will be counted toward the class participation part of the grade. Team member feedback will be considered for the instructor’s class participation assessment.
All students are expected to contribute to the classroom and behave professionally throughout the semester. Your learning activity is crucial to building a strong foundation for your future career.
Assignments sent via email will NOT be accepted/graded and will not receive credits. If you encounter issues with uploading your files to the course website, you should communicate with IT support.
Missing/Late Submissions
Missed final exams and class assignments will receive a grade of zero. Missed project submissions will result in a zero grade for all team participants. Non-compliance with the group project assignment will result in a zero grade for the free rider.
Late deliverables will be penalized with 4% off for every hour of delay, but not lower than 40% of the assignment grade.
Schedule conflicts for the final exam must be resolved 2 weeks before the final exam. You should contact me at least two weeks prior to the exam date and let me know. Last-minute requests will not be entertained.
Tentative List of Topics
Please note that this schedule may be adjusted.
| Class # | Topic | Reading (before the class) | Assignment (due EOW) |
| 1 | Intro to Data Mining & R Software | DMT – Chapter 1&3 | Syllabus Quiz (not graded) |
| 2 | Data Exploration and Preprocessing | DMT – Chapter 5 RDS – Chapter 1 & 3 |
Quiz 1, HW 1 |
| 3 | Prediction Models | DMT – Chapter 6 ISLR – Chapter 3 |
Quiz 2, Project Milestone 1 |
| 4 | Classification Models | DMT – Chapter 6 ISLR – Chapter 4.1-4.3 |
Quiz 3, HW 2 |
| 5 | Decision Trees | DMT – Chapter 7 ISLR – Chapter 8 |
Quiz 4, Milestone 1.5 |
| 6 | Cluster Analysis | DMT – Chapter 13 ISLR – Chapter 12.4 |
Quiz 5, HW 3 |
| 7 | Predictive Modeling Review | Review | Quiz 6, Milestone 2 (soft DL) |
| 8 | Course Projects | Milestone 3, Project peer review | |
| 03/07-03/09 | Final Exam |
*EOW=end of the learning week. EOW, for the purposes of the class, is determined during the first week of classes.
Disclaimer
This syllabus represents current plans and objectives. As we go through the semester, those plans may need to change to enhance the class learning opportunity. Such changes, communicated clearly, are not unusual and should be expected. If the course schedule encounters any modifications, the updates will be released in a separate document on the syllabus page of the course website.
To print: Right-click and choose “Print,” then follow your browser’s print settings.
To download: Right-click and choose “Print,” then select “Save as PDF.”