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
- Files:
-
-
(Preview, Accepted manuscript, pdf, 1.0MB, Terms of use)
-
- Publisher copy:
- 10.1145/3604237.3626857
Authors
+ European Commission
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)
+ Engineering and Physical Sciences Research Council
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
- Copyright holder:
- Association for Computing Machinery
- Copyright date:
- 2023
- Rights statement:
- © 2023 Association for Computing Machinery.
- Notes:
-
This is the accepted manuscript version of the paper. The final version is available online from Association for Computing Machinery at https://dx.doi.org/10.1145/3604237.3626857
This research was funded in whole or in part by the European Commission (grant number 952215). For the purpose of Open Access, the author has applied a CC BY public copyright licence to any Author Accepted Manuscript version arising from this submission.
| This is the accepted manuscript version of the article. The final version is available online from Association for Computing Machinery at https://doi.org/10.1145/3604237.3626857
- Licence:
- CC Attribution (CC BY)
If you are the owner of this record, you can report an update to it here: Report update to this record