DePauw University

School of Business and Leadership

BUS 310 Syllabus
Business Analytics III: Predictive and Prescriptive Business Analytics
Fall 2024

Professor: Dr. Yanchao Yang

Email: [email protected]
Office: Harrison Hall 103

Class Sessions: 2:50 pm – 3:50 pm MWF

Classroom: Harrison Hall 102
Office Hours: 10:20 AM -11:20 AM MWF or by appointment
Textbook: All course materials are open-access and will be provided for free
Prerequisites: A regression course (any regression course such as BUS 305, MATH
341, ECON 450) and BUS 210 or consent of the instructor.

Course Description
The application of big data, machine learning, and AI is increasingly used in the business world
to evaluate and improve business decisions. The ability to collect, analyze, and utilize data to
inform important decisions is a critical skill for modern business students. This course will
introduce students to the growing application of big data, AI, as well as predictive and
prescriptive analytics to answer business questions. Students will examine business cases where
data analytics have enabled better decision-making in areas of accounting, economics, finance,
management, and marketing. This course will familiarize students with open-source
programming language, Python, to analyze specific business cases.

1
Student Outcomes
Students will be able to:
1) Understand the big picture of big data, machine learning, and AI as a transformative force
in the world of modern business.
2) Apply advanced analytics to predict future trends and prescribe actionable strategies.
3) Become proficient in using Python for machine learning.
4) Apply the techniques of predictive and prescriptive business analytics to examples in
marketing, finance, management and entrepreneurship, accounting, and economics.
5) Engage in comprehensive research by writing an analytical paper that demonstrates the
ability to synthesize data insights and propose business solutions.
This will enable students to meet the following DePauw University Purpose and Aims:
5. Identify and solve well-defined and ill-defined problems.
6. Demonstrate competency with varied forms of data analysis.
7. Demonstrate knowledge of technology and its implications in society
8. Develop capacities for clear, thorough, and independent thought.
9. Clearly express their ideas and the ideas of others

Course Grading
To assess the extent to which students have acquired the skills necessary for a strong foundation
in predictive and prescriptive business analytics, the course grading components are listed below:
Class Attendance and Participation 15%
Pre-midterm Assignments 25%
Midterm 20%
Group Cases 30%
Final Presentations 10%
Total Grade 100%

Description of Grade Components

Class Attendance and Participation

The class sessions are intended to be personal and interactive, so attendance and participation
are essential.
Attendance is required and is part of the grade. Students are allowed three excused absences,
but an excused absence requires an email to the professor prior to the class session.
Participation in class sessions is a significant part of your grade. Students will be encouraged to
share with the class what they are learning during a module. Because this field is so new and
dynamic, each student will be able to provide unique insights from their personal learning
experience. Sometimes participation is answering questions and sometimes it is asking

2
questions. There is no need to be an expert to fully participate.

Pre-midterm Assignments
Students will complete two individual assignments before the midterm. These assignments give
students experience using Python for business analytics.

Midterm
There will be a midterm exam. Details about the midterm will be announced later.

Group Cases
There will be five group cases. For each case you will work in groups of 2 or 3 students. These
case studies will leverage the methods that you learn in class to generate insight from data and
should include in-depth data analysis, intuition, and careful interpretation of the results.

Presentation
During the last week of the semester, each group will give a presentation on one of their case
studies. Each presentation will be 15 - 20 minutes. There should be slides where you discuss
your questions, what models you used to answer the question, and your main takeaway form
the case study.

Accommodation for Documented Disabilities

It is the policy and practice of DePauw University to provide reasonable accommodations for
students with properly documented disabilities. Written notification from Student Disability
Services is required. If you are eligible to receive an accommodation and would like to request
it for this course, please contact Student Disability Services for a confidential discussion in UB
208 or by phone at 658-6267.

Academic Dishonesty
Please be sure to always indicate if you got help and exactly how. Copying your friend’s work,
whether written or electronically is cheating. It is plagiarism to turn in written work generated
by AI in place of your own. You may use AI tools (such as ChatGPT) to help you write more
clearly or solve a problem, as long as you clearly identify and cite the AI.

Respect
This course is designed for learning, which is best achieved by asking questions, thinking things
through, and even making mistakes. Please treat your professor and all of your classmates with
respect – we are all on our own journey of learning. If anyone has concerns about the behavior
of other people in the class, please let me know right away.

3
 Course Outline
Modules Topics
Introduction to • The Growing Role of Analytics in Business
Module 1
Business Analytics in • Big Data and AI in Business Decision Making
the Age of AI • Ethics in Big Data and AI
• Overview of Predictive and Prescriptive Analytics
Regression and • Machine Learning Overview
Classification • Supervised vs. Unsupervised Learning
Module 2

• Review of linear regression

• Logistic regression

Data Handling and • Introduction to Python for Data Analysis

Module 3

Computational Tools

Introduction to • Decision Trees and Random Forests

Module 4

Predictive Analytics • Support Vector Machines

and Machine Learning • Gradient Boosting Machines

Prediction Evaluation • Confusion Matrix

Module 5

• ROC Curve
• Cross-validation

Advanced Machine • Neural Networks

Module 6

Learning Models • Deep Learning Basics

Machine Learning • Machine Learning Applications in Finance,

Module 7

Applications in Economics, Marketing, Accounting, and Management

Business Disciplines

Introduction to • Integer Programming and Non-linear Programming

Module 8

Prescriptive Analytics • Multi-criteria Decision Making

Final Presentations • Group Presentations

Module 9