BAIT509 - Business Applications of Machine Learning

BAIT509 - Business Applications of Machine Learning

This is the home page for BAIT 509 at the University of British Columbia. This course is and introduction to machine learning concepts, such as model training, model testing, generalization error and overfitting. Exposure to a variety of machine learning techniques, with deeper exploration of a few chosen techniques. Forming good scientific questions to address business objectives with machine learning. Python will be the primary programming language used.

Please see the syllabus for more information about the course. Current students should refer to the UBC Canvas course website for the most up-to-date content and announcements.

Learning Objectives

By the end of the course, students are expected to be able to:

  1. Describe fundamental machine learning concepts such as: supervised and unsupervised learning, regression and classification, overfitting, training/validation/testing error, parameters and hyperparameters, and the golden rule.

  2. Broadly explain how common machine learning algorithms work, including: naïve Bayes, k-nearest neighbors, decision trees, support vector machines, and logistic regression.

  3. Identify when and why to apply data pre-processing techniques such as scaling and one-hot encoding.

  4. Use Python and the scikit-learn package to develop an end-to-end supervised machine learning pipeline.

  5. Apply and interpret machine learning methods to carry out supervised learning projects and to answer business objectives.

Teaching Team

Name

Position

Email

Joel Ostblom

Instructor

joel.ostblom@ubc.ca

Ali Seyfi

TA

Harsh Sharma

TA

Pranav Garg

TA

Class Meetings

#

Topic

Link

1

Introduction to machine learning and decision trees

Lecture 1

2

Splitting and Cross-validation

Lecture 2

3

Baseline, k-Nearest Neighbours

Lecture 3

4

SVM with RBF Kernel and Feature Preprocessing

Lecture 4

5

Preprocessing Categorical Features and Column Transformer

Lecture 5

6

Naive Bayes and Hyperparameter Optimization

Lecture 6

7

Linear Models

Lecture 7

8

Business Objectives/Statistical Questions and Feature Selection

Lecture 8

9

Classification and Regression Metrics

Lecture 9

10

Multi-Class, Pandas Profiling, Finale

Lecture 10

Assessments

Assessment

Due

Weight

Assignment 1

Jan 18

20%

Quiz

Jan 24

10%

Assignment 2

Jan 26

20%

Assignment 3

Feb 2

20%

Final Project

Feb 12

30%

All assessments will be submitted through UBC Canvas.

Office Hours

Teaching Member

When

Where

Joel Ostblom

Thursdays 2 - 3 PM PST

Zoom link on Canvas