EconPapers    
Economics at your fingertips  
 

Agent based model calibration using machine learning surrogates

Francesco Lamperti, Andrea Roventini and Amir Sani
Additional contact information
Francesco Lamperti: Université Panthéon-Sorbonne - Paris 1 (UP1)
Amir Sani: Université Panthéon-Sorbonne X

Sciences Po publications from Sciences Po

Abstract: Efficiently calibrating agent-based models (ABMs) to real data is an open challenge. This paper explicitly tackles parameter space exploration and calibration of ABMs by combining machine-learning and intelligent iterative sampling. The proposed approach “learns” a fast surrogate meta-model using a limited number of ABM evaluations and approximates the nonlinear relationship between ABM inputs (initial conditions and parameters) and outputs. Performance is evaluated on the Brock and Hommes (1998) asset pricing model and the “Islands” endogenous growth model Fagiolo and Dosi (2003). Results demonstrate that machine learning surrogates obtained using the proposed iterative learning procedure provide a quite accurate proxy of the true model and dramatically reduce the computation time necessary for large scale parameter space exploration and calibration.

Keywords: Agent based model; Calibration; Machine learning; Surrogate; Meta-model (search for similar items in EconPapers)
JEL-codes: C15 C52 C63 (search for similar items in EconPapers)
New Economics Papers: this item is included in nep-big, nep-cmp, nep-hme and nep-ore
Date: 2018-05
References: View references in EconPapers View complete reference list from CitEc
Citations: Track citations by RSS feed

Published in Journal of Economic Dynamics and Control, 2018, vol. 90, pp.366-389

Downloads: (external link)
https://spire.sciencespo.fr/hdl:/2441/13thfd12aa8r ... on-flamperti.pdf.pdf (application/pdf)

Related works:
Journal Article: Agent-based model calibration using machine learning surrogates (2018) Downloads
Working Paper: Agent-Based Model Calibration using Machine Learning Surrogates (2017) Downloads
Working Paper: Agent-based model calibration using machine learning surrogates (2017) Downloads
Working Paper: Agent-Based Model Calibration using Machine Learning Surrogates (2017) Downloads
Working Paper: Agent-Based Model Calibration using Machine Learning Surrogates (2017) Downloads
Working Paper: Agent-Based Model Calibration using Machine Learning Surrogates (2017) Downloads
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spo:wpmain:info:hdl:2441/13thfd12aa8rmplfudlgvgahff

Access Statistics for this paper

More papers in Sciences Po publications from Sciences Po Contact information at EDIRC.
Bibliographic data for series maintained by Spire @ Sciences Po Library ().

 
Page updated 2019-10-19
Handle: RePEc:spo:wpmain:info:hdl:2441/13thfd12aa8rmplfudlgvgahff