Machine Learning for Economics

Module description

Machine Learning is likely to have a big impact on Economics. In the era of so called ‘Big Data’, machine learning algorithms provide an extremely useful toolkit for prediction (regression), classification and clustering data. For example, machine learning algorithms can be used to find and cluster together similar consumer reviews, and lasso and ridge regression allow new kinds of econometric analysis to meaningfully analyse datasets with more variables than observations. This module introduces students to these new techniques, applying them to real datasets. Students will explore the trade-offs between expressiveness of datasets, and over-fitting, allowing them to understand how best to apply these techniques in economics.

Full module specification

Module title:	Machine Learning for Economics
Module code:	BEE3066
Module level:	3
Academic year:	2023/4
Module lecturers:	Dr Pradeep Kumar - Convenor
Module credit:	15
ECTS value:	7.5
Pre-requisites:	BEE2031 or BEE2041
Co-requisites:
Duration of module:	Duration (weeks) - term 1: 11

Module aims

This module will enable students to understand, apply and interpret findings from the commonly used predictive algorithms.

A student undertaking this module should have a good grasp of intermediate econometrics and some experience with a programming language.

ILO: Module-specific skills

1. illustrate the key characteristics of the popularly used machine learning algorithms.
2. interpret and report the findings of the machine learning methods using a programming language.

ILO: Discipline-specific skills

3. explain the commonly used supervised and unsupervised methods in machine learning.
4. assess the role played by prediction problems in economics.

ILO: Personal and key skills

5. exemplify quantitative analysis and logical thinking.
6. demonstrate programming skills.

Learning activities and teaching methods (given in hours of study time)

Scheduled Learning and Teaching Activities	Guided independent study	Placement / study abroad
27	123

Details of learning activities and teaching methods

Category	Hours of study time	Description
Schedule learning and teaching	22	Lectures
Schedule learning and teaching	5	Tutorials

Formative assessment

Form of assessment	Size of the assessment (eg length / duration)	ILOs assessed	Feedback method
In Class Exercises / Homework	Weekly in Lectures and Fortnightly in tutorials	1-6	Verbal/ ELE

Summative assessment (% of credit)

Coursework	Written exams	Practical exams
100	0	0

Details of summative assessment

Form of assessment	% of credit	Size of the assessment (eg length / duration)	ILOs assessed	Feedback method
Homework Assignment	30	1 problem set with 10 questions	1-6	Verbal/ELE
Term Project	70	3000 words	1-6	Verbal/ELE
	0
	0
	0
	0

Details of re-assessment (where required by referral or deferral)

Original form of assessment	Form of re-assessment	ILOs re-assessed	Timescale for re-assessment
Homework Assignment	Homework Assignment 30%	1-6	August/September reassessment period
Term Project	Term Project 70%	1-6	August/September reassessment period

Syllabus plan

Introduction to machine learning
Linear regression
Classification models
Resampling methods
Linear model Selection and regularization
Tree based methods
Support vector machines
Unsupervised learning

Note: The syllabus plan is tentative.

Indicative learning resources - Basic reading

Basic reading:

James, G., Witten, D., Hastie T. and Tibshirani, R. (2017) An Introduction to Statistical Learning (with Applications in R), Springer.

Geron, A. (2019), Hands-On Machine Learning with Scikit-Learn and TensorFlow: Concepts, Tools, and Techniques to Build Intelligent Systems, O’Reilly.

Rogers, S. and Girolami, M (2016), A First Course in Machine Learning, second edition, Chapman and Hall/CRC.

McCarthy, R.V., McCarthy, M.M., Ceccucci, W and Halawi, L. (2019), Applying Predictive Analytics: Finding Value in Data, Springer.

Module has an active ELE page?

Yes

Origin date

11/03/2019

Last revision date

11/03/2019