Machine Learning
Our fourth course lays a foundation of the two largest areas in machine learning: supervised and unsupervised learning. Instructors will demonstrate how machine learning techniques are applied to business problems, as well as how to implement these techniques using real life data.
Course Objectives
After completing this course, participants will be able to:​
-
Distinguish between supervised and unsupervised learning techniques
-
Explain the different types of machine learning models and the problems each can solve
-
Identify if a problem requires a regression, classification, or clustering module
-
Identify a useful metric for the business problem and optimize a model against it
-
Prep unclean data (data with outliers and/or missing values)
-
Identify model features and access accuracy of models
-
Apply and explain clustering and decision trees
Module 1: Regression
-
Introduction to supervised learning and regression
-
Probability and statistics review
-
Exploratory Data Analysis
-
Linear Regression (Ordinary Least Squares)
-
Polynomial Regression
-
Access accuracy of models
-
Overfitting vs Underfitting
Module 2: Regularization
-
Cross-validation and measuring generalizability
-
Overfitting vs Underfitting with Regularization
-
Variable Selection (Step-wise Regression and Best Subset Selection)
-
Ridge & Lasso Regression
-
Partial Least Squares Regression
Module 3: Generalized Linear Modeling
-
Intro to generalized linear modeling (GLM)
-
Accessing accuracy of GLM models
-
Logistic & Probit Regression
-
Poisson Regression
Module 4: Decision Trees
-
Introduction to Decision Trees
-
Building Classification and Regression Trees
-
Bagging and Random Forests
-
Boosting
Module 5: Unsupervised Learning
-
Introduction to Unsupervised Learning
-
Clustering
-
Feature engineering for clustering
-
Principal Component Analysis
-
Pairing supervised and unsupervised learning