Course Catalogue

View Specification Document | Reading List

Agent-based modelling (ABM) is developed based on the idea that the world can be modelled using agents, an environment, and a description of agent-agent and agent-environment interactions. It combines the elements of complex systems, evolutionary programming, emergence, computational sociology, game theory, multi-agent systems and reinforcement learning. The course focuses on applying ABM in economic systems and financial markets starting by introducing underlying mathematical and economic concepts. The students will be trained to critically analyse the assumptions and limitations of ABM and use programming languages to set up appropriate models to solve economic and financial problems.

One two-hour lecture per week for 10 weeks (on-campus)

One one-hour lab per week for 10 weeks (on-campus)

Asynchronous learning activities will include online programming practices and directed reading for approximately 5 hours.

Students must be registered on one of the associated programmes listed in this course specification.

None

None

ILO (covered)

Reassessments are normally available for all courses, except those which contribute to the Honours classification. Where, exceptionally, reassessment on Honours courses is required to satisfy professional/accreditation requirements, only the overall course grade achieved at the first attempt will contribute to the Honours classification. For non-Honours courses, students are offered reassessment in all or any of the components of assessment if the satisfactory (threshold) grade for the overall course is not achieved at the first attempt. This is normally grade D3 for undergraduate students and grade C3 for postgraduate students. Exceptionally it may not be possible to offer reassessment of some coursework items, in which case the mark achieved at the first attempt will be counted towards the final course grade. Any such exceptions for this course are described below. 

The Hackathon and presentation assessment cannot be reassessed as it is a group task.

This course aims at providing students with:

■ An in-depth understanding of agent-based models including underlying assumptions and limitations, and their use in computational economics and finance.

■ The ability to simulate and analyse agent-based models including reinforcement learning models.

■ The ability to critically evaluate the claims made by scientific papers in the field of agent-based modelling in economics and finance.

By the end of this course students will be able to:

1. Discuss what agent-based modelling is and why and when it is helpful.

2. Evaluate methods that can be used to model and simulate agent behaviours in strategic interaction and predict/analyse possible outcomes of such interaction.

3. Design and implement agent-based simulations and reinforcement learning models.

4. Analyse how different agent-based models contribute to explanations of the properties of economic systems and financial markets.

5. Validate agent-based models against the economic and financial data.

6. Develop teamworking skills through collaboration with peers on coding to solve complex finance problems.

Students must submit at least 75% by weight of the components (including examinations) of the course's summative assessment.