Centre for Econometric Analysis

Delivered by Dr Jan Novotny - running from the 8^th July 2025 to the 12^th August 2025.

Course overview
This course offers an applied introduction to machine learning, focusing on real-world implementation in finance. The core objective is to demystify machine learning and equip you with the skills and understanding needed to analyse your own datasets independently. By the conclusion of the course, you will be able to integrate these analytical methods into your daily workflow, enhancing your data-driven decision making and problem-solving capabilities. Each session combines theory with practical exercises, ensuring you develop both conceptual understanding and implementation skills. Expect to spend one/two hours a week to practice the machine learning techniques covered in the sessions.

Benefits
■ You will be introduced to basic concepts of machine learning, which is the
scientific study of algorithms and statistical models that computer systems use to perform a specific task without using explicit instructions, relying on patterns and inference instead
■ You will learn how to include machine learning models into your daily workflow with practical examples
■ You will learn how to code machine learning algorithms independently
■ You will implement a number of different machine learning methods ranging from ordinary least squares, regularised linear regressions, decision trees and forest, boosting, to neutral networks, understanding when each is applicable

Course prerequisites
You are expected to have a basic knowledge of Python (being able to run 
simple commands preferably using the Jupyter Notebooks), and a basic knowledge of Mathematics and Statistics. 

Target audience
This course is particularly useful to both professionals and researchers working in fields where there is demand for quantitative data-based decisions.

Schedule: 
8^th July 2025 to the 12^th August 2025.

Fees:
£340 City St George's Students, Alumni and Staff
£476 External Students
£680 External Non-Student

Registration, payment and cancellation policy

Payment of course fees is required prior to the course start date. In case a course is cancelled, registered participants will receive the full refund.

Registration closes 7-calendar days prior to the start of the course. Please use your University email address if purchasing City St George's/Bayes students, Alumni, Staff or External students rate tickets.

A 15% discount is available for groups of three or more participants. Please email faculty.administration@citystgeorges.ac.uk before purchasing your tickets if you are a group of three or more people. 

Please use your University email address to receive the student rate. 

Delivered by Professor Giovanni Urga - running from the 23^rd October 2025 to the 13^th November 2025.

Course overview 

The course covers several theoretical and empirical topics in financial econometrics providing a comprehensive presentation of the econometric methods applied to finance. Topics include: forecasting and forecast evaluation, estimation methods such as GMM and MLE, univariate and multivariate GARCH models, and realised and stochastic volatility models, 
measurement techniques and tests for contagion, principal components and factor analysis, the use of Autometrics in model selection in presence of a large number of regressors. The theory is illustrated in practice modelling interest rates, asset prices and forex time series at several temporal frequencies.

See more information here: Courses and webinars | Bayes Business School (city.ac.uk)

Benefits
■ You will be introduced to the statistical analysis of time series, autoregressive–moving-average (ARMA) models, and forecasting evaluation criteria
■ You will learn theoretical and practical tools of univariate, multivariate GARCH volatility models
■ You will learn to identify and measure contagion between markets
■ You will be taught theoretical and practical tools of high frequency data and the impact of market announcements
■ You will practise on practical econometric and financial problems

Target audience
This course is particularly useful to professionals working in the financial  industry, consultancy firms, Central Banks, regulatory authorities, public and 
private research centres.

Course prerequisites
Participants are expected to have a quantitative background. Knowledge of the fundamentals of econometrics, derivatives, quantitative asset pricing theory will help participants to obtain the maximum benefit from the course.

Schedule: 
23rd October 2025 - 13th November 2025. 

Fees:
£240 City St George's Students, Alumni and Staff
£360 External Students
£480 External Non-Student

Registration, payment and cancellation policy

Payment of course fees is required prior to the course start date. In case a course is cancelled, registered participants will receive the full refund.

Registration closes 7-calendar days prior to the start of the course. Please use your University email address if purchasing City St George's/Bayes students, Alumni, Staff or External students rate tickets.

A 15% discount is available for groups of three or more participants. Please email faculty.administration@citystgeorges.ac.uk before purchasing your tickets if you are a group of three or more people. 

Please use your University email address to receive the student rate. 

Delivered by Professor Giovanni Urga - running from the 2^nd September 2025 to the 23^rd September 2025.

Course overview: 

There is huge body of literature applying panel data techniques using stock market and banking data. In this course, we will 
present most important panel data techniques for stationary and nonstationary panels. We will discuss the importance of modellingheterogeneity and we will discuss static and dynamic models, introducing the crucial distinction between fixed and random effects. Practical applications using financial (stocks, interest rates) and banking (accounting) datasets will be delivered using Stata, which is the most comprehensive econometric software for dealing with panel data analysis.

Benefits:
■ You will learn how to handle and summarise panel datasets.
■ You will learn a large number of panel data techinques for stationary and nonstationary variables.
■ You will learn how to implement panel data analysis using econometric software.

Target audience: 

This course is particularly useful to professionals working in the financial industry, consultancy firms, Central Banks, regulatory authorities, public and private research centres.

Course prerequisites:

The course requires intermediate knowledge in statistics and econometrics for economics and finance. Knowledge of the fundamentals of financial stability and systemic risk will help participants to obtain the maximum benefit from the course. 

Schedule: 
2nd September 2025 - 23rd September 2025. 

Fees:
£240 City St George's Students, Alumni and Staff
£360 External Students
£480 External Non-Student

Registration, payment and cancellation policy

Payment of course fees is required prior to the course start date. In case a course is cancelled, registered participants will receive the full refund.

Registration closes 7-calendar days prior to the start of the course. Please use your University email address if purchasing City St George's/Bayes students, Alumni, Staff or External students rate tickets.

A 15% discount is available for groups of three or more participants. Please email faculty.administration@citystgeorges.ac.uk before purchasing your tickets if you are a group of three or more people. 

Please use your University email address to receive the student rate. 

Delivered by Dr Jan Novotny - running from the 4^th September 2025 to the 9^th October 2025.

Course overview 

This course will introduce the new field of quantum machine learning with application in Finance. The objective is to equip the audience with the foundations of the quantum computations and the key quantum machine learning methods. The methods will be set within the standard machine learning workflow and applied on real financial dataset. The quantum algorithms will be run on real quantum computers. 

The course consists of six 2-hour long sessions, each of which introducing a new topic and deepening the knowledge gathered in the previous ones. You are expected to spend at least one hour of self-study per week to review and practice the techniques covered in the sessions.

Benefits

You will be introduced to concepts of the quantum computations and the key notion of qubit. You will see number of standard operations we can do with one or more qubits including things like quantum teleportation.

You will learn two machine learning methods: the quantum support vector machine, and quantum neural network. We will also review the elements of the machine learning. Subsequently, you will be guided to set the workflow such that the quantum machine learning methods can be included into your standard workflow. Target audience This course is particularly useful to both professionals and researchers working with machine learning techniques, who are keen to extend knowledge to the new quantum tools.

Course prerequisites

Delegates are expected to have basic knowledge of Python (being able to run simple commands preferably using the Jupyter Notebooks), and basic knowledge of Mathematics and Statistics. Any prior knowledge of Quantum Physics is not required.

Registration, payment and cancellation policy

Payment of course fees is required prior to the course start date.

In case a course is cancelled, registered participants will receive the full refund.

Registration closes 7-calendar days prior to the start of the course.

A 15% discount is available for groups of three or more participants.

Please email faculty.administration@citystgeorges.ac.uk before purchasing your tickets if you are a group of three or more people. 

Please use your University email address to receive the student rate.