Machine Learning
Machine Learning is an elective 10 credit course and therefore students are expected to input approximately 100 hours of study into the course. The total number of contact hours is 15 hours. This leaves 85 hours for private study.
Delivery
This module consists of 2-hour lectures per day for 5 days, plus a 1-hour tutorial per day. There will be optional clinics on the last day of the course. The dates of each lecture are confirmed closer to the start of each term.
Study Hours
Approximately 100 hours of study, of which 15 are contact hours and 85 are private study.
Software Used
Stata
Credits
10 CATS credits
Programme Faculty
Programme Faculty
Key Outcomes
- —Implement factor-importance detection
- —Perform signal-from-noise extraction
- —Evaluate correct model specification
- —Understand model-free classification, both from a data-mining and a causal perspective
Desired Skills
- —Engage in abstract thinking by extracting the essential features of complex systems to facilitate problem solving and decision-making
- —Communicate and present complex arguments in oral and written form with clarity and succinctness
- —Present, interpret and analyse information in numerical form
- —Utilise effectively statistical and other packages
- —Apply basic statistical techniques to analyse economic and financial datasets
- —Work effectively both individually and within a team environment
Lecture Programme
- WK 01
Lecture 1: The Basics of Machine Learning I
- ·Supervised vs. unsupervised learning
- ·Regression vs. classification problems
- ·Inference vs. prediction
- ·Sampling vs. specification error
- WK 02
Lecture 2: The Basics of Machine Learning II
- ·Parametric vs. non-parametric models
- ·The trade-off between prediction accuracy and model interpretability
- ·Measuring the quality of fit: in-sample vs. out-of-sample prediction power
- ·Goodness-of-fit indices
- ·The bias-variance trade-off and the Mean Square Error (MSE) minimization
- WK 03
Lecture 3: Simulation, Resampling and Validation Methods I
- ·Logic and functioning of a Monte Carlo experiment
- ·Implementing Monte Carlo experiments
- ·The logic of the Bootstrap
- ·Bootstrapping standard errors
- WK 04
Lecture 4: Simulation, Resampling and Validation Methods II
- ·Cross-Validation
- ·The validation set approach
- ·Leave-One-Out Cross-Validation
- ·K-fold cross-validation
- ·The Stata package crossfold
- WK 05
Lecture 5: Non-parametric regression: local methods I
- ·Beyond parametric models: the "why" and the "how"
- WK 06
Lecture 6: Non-parametric regression: local methods II
- ·Nearest-neighbor regression
- ·Kernel-based regression
- ·The Stata npregress command
- WK 07
Lecture 7: Non-parametric regression: global methods I
- ·Polynomial and series regression
- ·Spline regression
- WK 08
Lecture 8: Non-parametric regression: global methods II
- ·Generalized additive models
- WK 09
Lecture 9: Model Selection and Regularization I
- ·Subset Selection: Optimal, Forward and Backward subset selection
- WK 10
Lecture 10: Model Selection and Regularization II
- ·Shrinkage Methods: Lasso, Ridge, and Elastic regression
- WK 11
Lecture 11: Tree-Based Regression I
- ·An introduction to Regression Trees
- WK 12
Lecture 12: Applications using Stata II
- ·Bagging, Random Forests, and Boosting
Assessment
Online coursework submission with the support of your module lecturer and tutor. All sessions are conducted live online at a scheduled time and recorded for review.