Data Science for Economics and Finance

• Credit value: 30 credits at Level 6
• Coordinator: Professor Sandeep Kapur
• Lecturers: Dan Kaliski and Ilaria Peri
• Assessment: a two-hour-10-minute examination (70%) and a data-based project (30%)

While economic analysis of data to discover causal relations has been a long-standing tradition in economics and finance, the landscape has been altered by recent trends - the emergence of ‘big data’, the ease of gathering data through ‘web-scraping’, use of machine learning for predictive analysis in economic and business contexts. The ability to use open-source programming languages such as R and Python can provide economics graduates with skills that are highly valued in the job market. This module will help our graduates to meet that need.

This module will teach you the basic programming skills in languages - such as R and Python - and show how analysis of big data and machine learning can be useful in the design of economic policy and in the understanding of financial markets.

Indicative module syllabus

• Programming and Data
• Intro to data science: key issues and concepts; getting started with programming
• Boolean logic; conditionals; wildcards
• Loops; combining loops with conditionals
• Getting data (webscraping)
• Visualisation of data and statistical results

• Introduction to Machine Learning
• LASSO, ridge regression; discussion of overfitting, bias-variance trade-off
• Discrete outcomes; logit and probit
• Classifiers; decision trees

By the end of this module, you will:

• understand the basic programming and construct simple code
• be able to use webscraping techniques to gather data from diverse sources
• be able to deploy standard programmes to visualise data and perform statistical analysis
• understand and apply simple machine learning techniques.