Calibrating high frequency trading data to agent based models using approximate Bayesian computation

Simple item page
dc.contributor.advisorGebbie, Timothy
dc.contributor.authorGoosen, Kelly
dc.date.accessioned2021-08-04T10:44:55Z
dc.date.available2021-08-04T10:44:55Z
dc.date.issued2021
dc.date.updated2021-08-04T10:44:32Z
dc.description.abstractWe consider Sequential Monte Carlo Approximate Bayesian Computation (SMC ABC) as a method of calibration for the use of agent based models in market micro-structure. To date, there are no successful calibrations of agent based models to high frequency trading data. Here we test whether a more sophisticated calibration technique, SMC ABC, will achieve this feat on one of the leading agent based models in high frequency trading literature (the Preis-Golke-Paul-Schneider Agent Based Model (Preis et al., 2006)). We find that, although SMC ABC's naive approach of updating distributions can successfully calibrate simple toy models, such as autoregressive moving average models, it fails to calibrate this agent based model for high frequency trading. This may be for two key reasons, either the parameters of the model are not uniquely identifiable given the model output or the SMC ABC rejection mechanism results in information loss rendering parameters unidentifiable given insucient summary statistics.
dc.identifier.apacitationGoosen, K. (2021). <i>Calibrating high frequency trading data to agent based models using approximate Bayesian computation</i>. (). ,Faculty of Science ,Department of Statistical Sciences. Retrieved from http://hdl.handle.net/11427/33699en_ZA
dc.identifier.chicagocitationGoosen, Kelly. <i>"Calibrating high frequency trading data to agent based models using approximate Bayesian computation."</i> ., ,Faculty of Science ,Department of Statistical Sciences, 2021. http://hdl.handle.net/11427/33699en_ZA
dc.identifier.citationGoosen, K. 2021. Calibrating high frequency trading data to agent based models using approximate Bayesian computation. . ,Faculty of Science ,Department of Statistical Sciences. http://hdl.handle.net/11427/33699en_ZA
dc.identifier.ris TY - Master Thesis AU - Goosen, Kelly AB - We consider Sequential Monte Carlo Approximate Bayesian Computation (SMC ABC) as a method of calibration for the use of agent based models in market micro-structure. To date, there are no successful calibrations of agent based models to high frequency trading data. Here we test whether a more sophisticated calibration technique, SMC ABC, will achieve this feat on one of the leading agent based models in high frequency trading literature (the Preis-Golke-Paul-Schneider Agent Based Model (Preis et al., 2006)). We find that, although SMC ABC's naive approach of updating distributions can successfully calibrate simple toy models, such as autoregressive moving average models, it fails to calibrate this agent based model for high frequency trading. This may be for two key reasons, either the parameters of the model are not uniquely identifiable given the model output or the SMC ABC rejection mechanism results in information loss rendering parameters unidentifiable given insucient summary statistics. DA - 2021 DB - OpenUCT DP - University of Cape Town KW - agent based models KW - high frequency trading KW - calibration KW - approximate Bayesian computation KW - sequential Monte Carlo KW - stylised facts KW - market micro-structure LK - https://open.uct.ac.za PY - 2021 T1 - Calibrating high frequency trading data to agent based models using approximate Bayesian computation TI - Calibrating high frequency trading data to agent based models using approximate Bayesian computation UR - http://hdl.handle.net/11427/33699 ER - en_ZA
dc.identifier.urihttp://hdl.handle.net/11427/33699
dc.identifier.vancouvercitationGoosen K. Calibrating high frequency trading data to agent based models using approximate Bayesian computation. []. ,Faculty of Science ,Department of Statistical Sciences, 2021 [cited yyyy month dd]. Available from: http://hdl.handle.net/11427/33699en_ZA
dc.language.rfc3066eng
dc.publisher.departmentDepartment of Statistical Sciences
dc.publisher.facultyFaculty of Science
dc.subjectagent based models
dc.subjecthigh frequency trading
dc.subjectcalibration
dc.subjectapproximate Bayesian computation
dc.subjectsequential Monte Carlo
dc.subjectstylised facts
dc.subjectmarket micro-structure
dc.titleCalibrating high frequency trading data to agent based models using approximate Bayesian computation
dc.typeMaster Thesis
dc.type.qualificationlevelMasters
dc.type.qualificationlevelMSc
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
thesis_sci_2021_goosen kelly.pdf
Size:
3.5 MB
Format:
Adobe Portable Document Format
Description:
Download
License bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
license.txt
Size:
0 B
Format:
Item-specific license agreed upon to submission
Description:
Download
Collections
Masters