TBC
The collection, description and analysis of data has always been at the heart of central banks’ policymaking. In these activities, the imperative is to separate a consistent signal from the associated noise. Both the sources of data and the associated techniques for analysis have seen profound changes over the past decade or so: the relentless digitisation of most activities has led to the availability of many more datasets, collectively known as ‘Big Data’, while advances in computing power have led to new techniques for analysing these data sets, such as artificial intelligence (AI) and machine learning (ML). The convergence of new and generally richer sources of data with more sophisticated techniques for describing and summarising them does not necessarily translate into clear policy descriptions. This course will highlight the fundamentals of telling a clear story using data visualisation and analytics tools in a Central Bank setting
The course will be delivered by SEACEN faculty and will include a number of external experts from academia and central banking.
At the end of the course, participants should be able to: (1) have a basic understanding of data visualisation techniques; (2) have a thorough understanding of new, alternative or integrated data sets, i.e., Big Data; (3) be exposed to ML methodologies currently employed at central banks in both advanced and emerging-market economies; and (4) be familiar with the basic design AI tools their interpretation.
Economists working in all departments of central banks who are interested in learning about cutting-edge analysis that can be performed on new or alternative data sets. The large-scale nature of the data and the statistical techniques required for its analysis necessitate the use of statistical packages such as R and Python. A sound knowledge of statistics and data analytics is highly recommended. Only participants who complete 80% of the sessions will receive a certificate of completion.
We will be using several software packages in this course. Participants will need R and Python for most of the empirical illustrations. The week before the course, we will have an online introductory session on R with participants.
All potential topics will be delivered through a combination of lectures and exercises/workshops:
