IDEAS home Printed from https://ideas.repec.org/p/amz/wpaper/2022-30.html
   My bibliography  Save this paper

Calibrating Agent-based Models to Microdata with Graph Neural Networks

Author

Listed:
  • Farmer, J. Doyne
  • Dyer, Joel
  • Cannon, Patrick
  • Schmon, Sebastian

Abstract

Calibrating agent-based models (ABMs) to data is among the most fundamental requirements to ensure the model fulfils its desired purpose. In recent years, simulation-based inference methods have emerged as powerful tools for performing this task when the model likelihood function is intractable, as is often the case for ABMs. In some real-world use cases of ABMs, both the observed data and the ABM output consist of the agents' states and their interactions over time. In such cases, there is a tension between the desire to make full use of the rich information content of such granular data on the one hand, and the need to reduce the dimensionality of the data to prevent difficulties associated with high-dimensional learning tasks on the other. A possible resolution is to construct lower-dimensional time-series through the use of summary statistics describing the macrostate of the system at each time point. However, a poor choice of summary statistics can result in an unacceptable loss of information from the original dataset, dramatically reducing the quality of the resulting calibration. In this work, we instead propose to learn parameter posteriors associated with granular microdata directly using temporal graph neural networks. We will demonstrate that such an approach offers highly compelling inductive biases for Bayesian inference using the raw ABM microstates as output.

Suggested Citation

  • Farmer, J. Doyne & Dyer, Joel & Cannon, Patrick & Schmon, Sebastian, 2022. "Calibrating Agent-based Models to Microdata with Graph Neural Networks," INET Oxford Working Papers 2022-30, Institute for New Economic Thinking at the Oxford Martin School, University of Oxford.
  • Handle: RePEc:amz:wpaper:2022-30
    as

    Download full text from publisher

    File URL: https://www.inet.ox.ac.uk/files/10.48550_arxiv.2206.07570.pdf
    Download Restriction: no
    ---><---

    References listed on IDEAS

    as
    1. Lux, Thomas, 2018. "Estimation of agent-based models using sequential Monte Carlo methods," Journal of Economic Dynamics and Control, Elsevier, vol. 91(C), pages 391-408.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Kukacka, Jiri & Jang, Tae-Seok & Sacht, Stephen, 2018. "On the estimation of behavioral macroeconomic models via simulated maximum likelihood," Economics Working Papers 2018-11, Christian-Albrechts-University of Kiel, Department of Economics.
    2. Delli Gatti, Domenico & Grazzini, Jakob, 2020. "Rising to the challenge: Bayesian estimation and forecasting techniques for macroeconomic Agent Based Models," Journal of Economic Behavior & Organization, Elsevier, vol. 178(C), pages 875-902.
    3. Barde, Sylvain, 2020. "Macroeconomic simulation comparison with a multivariate extension of the Markov information criterion," Journal of Economic Dynamics and Control, Elsevier, vol. 111(C).
    4. Lux, Thomas, 2020. "Bayesian estimation of agent-based models via adaptive particle Markov chain Monte Carlo," Economics Working Papers 2020-01, Christian-Albrechts-University of Kiel, Department of Economics.
    5. Corrado Monti & Marco Pangallo & Gianmarco De Francisci Morales & Francesco Bonchi, 2022. "On learning agent-based models from data," Papers 2205.05052, arXiv.org, revised Nov 2022.
    6. Denis Koshelev & Alexey Ponomarenko & Sergei Seleznev, 2023. "Amortized neural networks for agent-based model forecasting," Papers 2308.05753, arXiv.org.
    7. Zila, Eric & Kukacka, Jiri, 2023. "Moment set selection for the SMM using simple machine learning," Journal of Economic Behavior & Organization, Elsevier, vol. 212(C), pages 366-391.
    8. Donovan Platt, 2022. "Bayesian Estimation of Economic Simulation Models Using Neural Networks," Computational Economics, Springer;Society for Computational Economics, vol. 59(2), pages 599-650, February.
    9. Nils Bertschinger & Oliver Pfante, 2020. "Early Warning Signs of Financial Market Turmoils," JRFM, MDPI, vol. 13(12), pages 1-24, November.
    10. Emna Mnif & Anis Jarboui & M. Kabir Hassan & Khaireddine Mouakhar, 2020. "Big data tools for Islamic financial analysis," Intelligent Systems in Accounting, Finance and Management, John Wiley & Sons, Ltd., vol. 27(1), pages 10-21, January.
    11. Kononovicius, Aleksejus, 2021. "Supportive interactions in the noisy voter model," Chaos, Solitons & Fractals, Elsevier, vol. 143(C).
    12. Tubbenhauer, Tobias & Fieberg, Christian & Poddig, Thorsten, 2021. "Multi-agent-based VaR forecasting," Journal of Economic Dynamics and Control, Elsevier, vol. 131(C).
    13. Ramis Khabibullin & Sergei Seleznev, 2022. "Fast Estimation of Bayesian State Space Models Using Amortized Simulation-Based Inference," Papers 2210.07154, arXiv.org.
    14. David Alaminos & M. Belén Salas & Manuel Á. Fernández-Gámez, 2023. "Quantum Monte Carlo simulations for estimating FOREX markets: a speculative attacks experience," Palgrave Communications, Palgrave Macmillan, vol. 10(1), pages 1-21, December.
    15. Ramis Khabibullin & Alexey Ponomarenko, 2022. "An empirical behavioral model of household’s deposit dollarization," Journal of Economic Interaction and Coordination, Springer;Society for Economic Science with Heterogeneous Interacting Agents, vol. 17(3), pages 827-847, July.
    16. Thomas Lux, 2022. "Bayesian Estimation of Agent-Based Models via Adaptive Particle Markov Chain Monte Carlo," Computational Economics, Springer;Society for Computational Economics, vol. 60(2), pages 451-477, August.
    17. Kukacka, Jiri & Kristoufek, Ladislav, 2021. "Does parameterization affect the complexity of agent-based models?," Journal of Economic Behavior & Organization, Elsevier, vol. 192(C), pages 324-356.
    18. Platt, Donovan, 2020. "A comparison of economic agent-based model calibration methods," Journal of Economic Dynamics and Control, Elsevier, vol. 113(C).
    19. Zhiming LONG & Rémy HERRERA, 2020. "Spurious OLS Estimators of Detrending Method by Adding a Linear Trend in Difference-Stationary Processes—A Mathematical Proof and Its Verification by Simulation," Mathematics, MDPI, vol. 8(11), pages 1-19, November.
    20. Majewski, Adam A. & Ciliberti, Stefano & Bouchaud, Jean-Philippe, 2020. "Co-existence of trend and value in financial markets: Estimating an extended Chiarella model," Journal of Economic Dynamics and Control, Elsevier, vol. 112(C).

    More about this item

    NEP fields

    This paper has been announced in the following NEP Reports:

    Statistics

    Access and download statistics

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:amz:wpaper:2022-30. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: INET Oxford admin team (email available below). General contact details of provider: https://edirc.repec.org/data/inoxfuk.html .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.