Conference item icon

Conference item

Gradient-assisted calibration for financial agent-based models

Abstract:
Agent-based modelling (ABMing) is a promising approach to modelling and reasoning about complex systems such as financial markets. However, the application of ABMs in practice is often impeded by the models’ complexity and the ensuing difficulty of performing parameter inference and optimisation tasks. This in turn has motivated efforts directed towards the construction of differentiable ABMs, enabled by recently developed effective auto-differentiation frameworks, as a strategy for addressing these challenges.
In this paper, we discuss and present experiments that demonstrate how differentiable programming may be used to implement and calibrate heterogeneous ABMs in finance. We begin by considering in more detail the difficulties inherent in constructing gradients for discrete ABMs. Secondly, we illustrate solutions to these difficulties, by using a discrete agent-based market simulation model as a case study. Finally, we show through numerical experiments how our differentiable implementation of this discrete ABM enables the use of powerful tools from probabilistic machine learning and conditional generative modelling to perform robust parameter inferences and uncertainty quantification, in a simulation-efficient manner.
Publication status:
Published
Peer review status:
Peer reviewed

Actions


Access Document


Publisher copy:
10.1145/3604237.3626857

Authors


More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author
More by this author
Institution:
University of Oxford
Division:
SSD
Role:
Author
More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Computer Science
Role:
Author


More from this funder
Funder identifier:
https://ror.org/00k4n6c32
Funding agency for:
Wooldridge, MJ
Calinescu, A
Grant:
952215
Programme:
Trustworthy AI - Integrating Learning, Optimisation and Reasoning (TAILOR)
More from this funder
Funder identifier:
https://ror.org/0439y7842
Funding agency for:
Wooldridge, MJ
Grant:
EP/W002949/1
Programme:
UKRI AI World Leading Researcher Fellowship


Publisher:
Association for Computing Machinery
Host title:
ICAIF '23: Proceedings of the Fourth ACM International Conference on AI in Finance
Journal:
4th ACM International Conference on AI in Finance More from this journal
Pages:
288-296
Publication date:
2023-11-25
Acceptance date:
2023-09-28
Event title:
4th ACM International Conference on AI in Finance (ICAIF 2023)
Event location:
New York, USA
Event website:
https://ai-finance.org/
Event start date:
2023-11-27
Event end date:
2023-11-29
DOI:
ISBN:
9798400702402


Language:
English
Keywords:
Pubs id:
1541047
Local pid:
pubs:1541047
Deposit date:
2023-10-04

Terms of use



Views and Downloads






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP