| Unit name | Machine Learning for Economic Analysis |
|---|---|
| Unit code | ECON30014 |
| Credit points | 20 |
| Level of study | H/6 |
| Teaching block(s) |
Teaching Block 1 (weeks 1 - 12) |
| Unit director | Dr. Hubner |
| Open unit status | Not open |
| Units you must take before you take this one (pre-requisite units) |
Students, for whom this unit is an optional unit: EFIM20011 Econometrics 1 (minimum mark of 60%) AND EITHER EFIM20036 Econometrics 2 (minimum mark of 60%) OR MATH20800 Statistics 2 (minimum mark of 60%) OR MATH20014 Mathematical Programming (minimum mark of 60%) |
| Units you must take alongside this one (co-requisite units) |
None |
| Units you may not take alongside this one |
None |
| School/department | School of Economics |
| Faculty | Faculty of Social Sciences and Law |
Why is this unit important?
The increasing availability of ‘big data’ about choices and characteristics of economic agents is altering the practice of creating knowledge through empirical economic analysis. The variety, volume, and velocity of new datasets are unprecedented. Dealing with these characteristics, not only offers a unique possibility to extract higher theoretical content from the data but also demands the adoption of appropriate tools such as modern machine learning methods for a sound and responsible use of the data.
How does this unit fit into your programme of study?
This unit addresses the creation of knowledge from data that is relevant to economic analysis by building on quantitative methods and economic theory from the first and second year.
An overview of content
The course aims to build a strong foundation of machine learning methods with a particular emphasis on the principles and goals that a different to classical econometric methods. This includes the role of model training and validation, model selection, tuning-parameters, computational considerations, and inference. We will broadly distinguish between supervised learning for regression (continuous choice variables) and supervised learning for classification (discrete choice).
As a starting point, we will re-visit logistic regression to connect these two concepts and then discuss more specific methods, including regularised linear regression such as LASSO, principal component analysis, deep learning and neural nets in the context of regression, as well as decision trees, and support vector machines in the context of classification. We will develop the theoretical foundations to analyse the properties of the discussed methods, learn how to implement them using statistical programming languages, and apply them to datasets to extract relevant information and create knowledge.
Throughout the course, we will discuss several use-cases from economics (e.g. consumer demand, two-sided matching on marriage markets, hedonic pricing models, et cetera) and analyse them through the lenses of economic theory, classical regression, and modern machine learning methods. We will discuss their respective strengths and weaknesses and justify the appropriate method to extract and identify the relevant characteristics from data.
How will students, personally, be different as a result of the unit
You should be able to critically judge the claims made regarding machine learning models and artificial intelligence tools. Further, you will have acquired the theoretical foundations to evaluate the eligibility, strengths, and weaknesses of a comprehensive toolkit to solve real-world problems.
Learning outcomes
At the end of this unit, students should:
Teaching will be delivered through a combination of large and small group classes, supported by online resources.
Tasks which help you learn and prepare you for summative tasks (formative)
Computer lab exercises
Tasks which count towards your unit mark (summative):
Written exam (2.5 hours). Evaluates all the learning outcomes.
When assessment does not go to plan
There are normally no reassessment opportunities for final year students. Where this unit is taken as a non-final year unit, reassessment will be through a 2.5 hour examination.
If this unit has a Resource List, you will normally find a link to it in the Blackboard area for the unit. Sometimes there will be a separate link for each weekly topic.
If you are unable to access a list through Blackboard, you can also find it via the Resource Lists homepage. Search for the list by the unit name or code (e.g. ECON30014).
How much time the unit requires
Each credit equates to 10 hours of total student input. For example a 20 credit unit will take you 200 hours
of study to complete. Your total learning time is made up of contact time, directed learning tasks,
independent learning and assessment activity.
See the University Workload statement relating to this unit for more information.
Assessment
The Board of Examiners will consider all cases where students have failed or not completed the assessments required for credit.
The Board considers each student's outcomes across all the units which contribute to each year's programme of study. For appropriate assessments, if you have self-certificated your absence, you will normally be required to complete it the next time it runs (for assessments at the end of TB1 and TB2 this is usually in the next re-assessment period).
The Board of Examiners will take into account any exceptional circumstances and operates
within the Regulations and Code of Practice for Taught Programmes.
