Machine Learning


This course will be an introduction to machine learning techniques and how to use them to help solve business problems. This course is designed for management, economics and finance students who are interested in learning modern, scalable, computational data analysis methods also known as machine learning, and apply them to business and social problems.
This is a hands-on course where students will be expected to use Python to implement solutions to various business problems. Prior experience with Python is required, and students should be familiar with basics Python data science libraries such as numpy, pandas, matplotlib, seaborn. Other programming knowledge, such as R, Matlab, Java, etc would be highly preferred.

General characterization





Responsible teacher

Qiwei Han


Weekly - Available soon

Total - Available soon

Teaching language



Available soon


This course does not require any textbook, because data science is a rapidly changing field and no textbook may cover all materials we will teach in the course. However, the following book is recommended for your reference:
Data Science for Business: What You Need to Know about Data Mining and Data-Analytic Thinking Machine Learning: The Art and Science of Algorithms that Make Sense of Data
Python for Data Analysis: Data Wrangling with Pandas, NumPy, and IPython 2nd Edition Python Data Science Handbook Essential Tools for Working with Data
Hands-on Machine Learning with scikit-learn, Keras, and Tensorflow

Teaching method

Students are required to bring own laptops for in-class exercises and quizzes. This course adopts learning-by-doing culture that allows students to implement machine learning pipeline through programming in Python. Most of class material will be in the Jupyter notebooks to facilitate reproducible practices.

Evaluation method

The overall evaluation of performance consists of 4 parts
•    Class participation through 6 quizzes (10%)
•    4 tri-weekly assignment (20%)
•    Course project (30%)
•    Final exam (40%)

Subject matter

•    Overview of the Machine Learning Process
1.    Understand Problem
2.    Map to Machine Learning formulation
3.    Machine Learning Concepts
4.    End-to-end Machine Learning Pipeline Development
1.    Setup the problem
2.    Feature Development
3.    Modeling
4.    Evaluation
5.    Deployment

•    Machine Learning Methods
1.    Supervised
1.    Logistic Regression
2.    KNN
3.    Trees
4.    Random Forests
5.    Ensemble Methods
2.    Unsupervised
1.    Clustering
2.    Dimensionality reduction
3.    Deep Learning
1.    Neural networks
2.    Convolutional neural networks
3.    Recurrent neural networks
4.    Other advances in the field
4.    Business applications
1.    Recommender systems
2.    Uplift modeling
•    Feature creation, feature engineering and feature selection
•    Interpretability and transparency
•    Ethics, Fairness and Bias