Objective

This course offers an introduction to the application of Python for Data Science and Machine Learning. In recent years, Data Science and Machine Learning have significantly influenced how central banks perform tasks such as market analysis, risk assessment and banking supervision. Python, as one of the leading programming languages for Data Science, plays a pivotal role in these areas.

Participants will learn how to use Python to analyse data, build machine learning models and support business decisions. The course begins with a basic introduction to Python, followed by a swift transition to its application in Data Science and Machine Learning. The primary libraries covered include NumPy, Pandas, Scikit-learn and Matplotlib, with occasional use of additional libraries.

Programming tasks and smaller projects will be conducted through practical exercises, either independently or in groups, fostering collaboration among participants.

By the end of the course, participants will be equipped to use Python for data analysis, model building and extending their knowledge autonomously. This will enable them to apply their skills to tasks and challenges in their respective central banks. Additionally, they will learn how to access online resources to independently explore and implement further approaches and methods.

Contents

Introduction to Python

- Basics and fundamental concepts

- Data structures in Python

- Data visualisation with Python

Data preparation and analysis

- Data retrieval and cleaning

- Descriptive statistics in Python

Machine Learning

- Regression and Classification

- Artificial Neural Networks

- Machine learning for central bank tasks

Case studies and projects

- Practical application of data science in central banks

- Project work and programming exercises

Starting on the second day, each session will begin with a Q&A slot, providing participants with the opportunity to discuss the previous day's content and address any challenges encountered during the practical exercises.

Target group

The course is designed for staff working in information technology, statistics, or research departments within central banks, as well as regulatory and supervisory authorities with an interest in applying machine learning methods with Python. It is not intended for individuals with extensive or advanced Python knowledge.

Minimal prior knowledge is required, as the necessary Python skills will be covered at the start of the course, making it suitable for participants with little to no experience. The course may also appeal to those looking to transition from the programming language R to Python.

Please note that the course will not delve deeply into the statistical foundations of the methods used.

Technical requirements

• Computer with microphone, camera, speakers, or headphones
• An up-to-date internet browser.

Participants should have access to their own computers with Python pre-installed (e.g., via Anaconda). Assistance with installation will be provided in advance if needed. Using two screens is highly recommended to facilitate participation and coursework.