BAIT 509: Business Applications of Machine Learning

Lecture 1 - Introduction to Machine Learning, the decision tree algorithm

Tomas Beuzen, 6th January 2020

1. Goals of the course and overview (5 mins)

Goals

  • Describe fundamental machine learning concepts;
  • Broadly explain how common machine learning algorithms work;
  • Implement a machine learning pipeline in Python; and,
  • Apply machine learning methods to carry out supervised learning projects and to answer business objectives.

Overview

  • 2 lectures per week (generally composed of lecture + class activity)
  • My office hours: 1-2pm Thursday ESB1045
  • TA office hours: 12-1pm Friday ESB1045
  • No lids down policy (kind of)
  • Additional resources here: https://canvas.ubc.ca/courses/35074/files/6546365?module_item_id=1558725
  • Use Piazza for Q&A
  • Grade:
    • 3 assignments during the course (60% each)
    • final group assignment (30%)
    • participation (10%): attendance at each lecture is worth 1% of your grade. Attendance will be taken using a Canvas quiz at the start of each lecture, let's do that now! (from now on, the quiz will only be open for the first 5 minutes of each lecture, so be on time!).

2. Lecture learning objectives

  • Describe the difference between supervised and unsupervised learning
  • Distinguish machine learning terminology such as features, targets, training, etc.
  • Broadly describe how the decision tree algorithm works
  • Develop a decision tree model using scikit-learn and the fit/predict paradigm
  • Describe the difference between parameters and hyperparameters in machine learning models

3. About me (5 mins)

  • From Australia