Skip to main content
Log in

Surrogate Modelling in (and of) Agent-Based Models: A Prospectus

  • Published:
Computational Economics Aims and scope Submit manuscript


A very timely issue for economic agent-based models (ABMs) is their empirical estimation. This paper describes a line of research that could resolve the issue by using machine learning techniques, using multi-layer artificial neural networks (ANNs), or so called Deep Nets. The seminal contribution by Hinton et al. (Neural Comput 18(7):1527–1554, 2006) introduced a fast and efficient training algorithm called Deep Learning, and there have been major breakthroughs in machine learning ever since. Economics has not yet benefited from these developments, and therefore we believe that now is the right time to apply multi-layered ANNs and Deep Learning to ABMs in economics.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Subscribe and save

Springer+ Basic
EUR 32.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or Ebook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.


  1. Even though we have to generate quite a lot of training data from the computationally heavy simulation model, this is necessary only once to train the surrogate model. Once the surrogate is in place, it can be use to replace the heavy model, precisely as the term “surrogate” would seem to imply. Note that the computational complexity of training the surrogate model on the training data might turn out to be quite high. It therefore seems reasonable to assume that this method is only applicable to a subclass of ABMs that benefit from using such emulators. I thank a referee for this observation.

  2. A possible candidate for such environmentally-aware, cognitive algorithms would be Hutter’s AIXI, see Hutter (2000).

  3. But not impossible in principle. For example, the global sensitivity analysis of a large-scale ABM such as the Eurace@Unibi Model was already performed using HPC clusters (Barde and van der Hoog 2017). Also, empirical validation is currently being done for medium-sized ABMs, and given the exponential increase in computing power is expected to yield results in the coming years.

  4. A side-remark must be made here on the computational complexity of the neural network training. Since it is not uncommon that ANNs have millions of weights that must be trained, this is by no means a simple feat.


  • Argote, L., & Greve, H. R. (2007). A behavioral theory of the firm—40 years and counting: Introduction and impact. Organization Science, 18(3), 337–349.

    Article  Google Scholar 

  • Azoff, E. (1994). Neural network time series forecasting of financial markets. Chichester: Wiley.

    Google Scholar 

  • Bacha, H., & Meyer, W. (1992). A neural network architecture for load forecasting. Proceedings of the IEEE International Joint Conference on Neural Networks, 2, 442–447.

    Google Scholar 

  • Barde, S. (2016). Direct comparison of agent-based models of herding in financial markets. Journal of Economic Dynamics and Control, 73, 329–353.

    Article  Google Scholar 

  • Barde, S. (2017). A practical, accurate, information criterion for Nth order Markov processes. Computational Economics, 50(2), 281–324.

    Article  Google Scholar 

  • Barde, S., & van der Hoog, S. (2017). An empirical validation protocol for large-scale agent-based models. Studies in Economics 1712, School of Economics, University of Kent.

  • Bengio, Y., Boulanger-Lewandowski, N., & Pascanu, R. (2013). Advances in optimizing recurrent networks. In IEEE international conference on acoustics, speech and signal processing (ICASSP) (pp. 8624–8628).

  • Brenner, T., & Werker, C. (2006). A practical guide to inference in simulation models. Papers on Economics and Evolution 2006-02, Philipps University Marburg, Department of Geography.

  • Cyert, R. M., & March, J. G. (1963). A behavioral theory of the firm. Englewood Cliffs: Prentice Hall.

    Google Scholar 

  • Dawid, H., & Fagiolo, G. (2008). Agent-based models for economic policy design: Introduction to the special issue. Journal of Economic Behavior & Organization, 67(2), 351–354. (special issue on Agent-based models for economic policy design).

    Article  Google Scholar 

  • Dawid, H. & Harting, P. (2012). Capturing firm behavior in agent-based models of industry evolution and macroeconomic dynamics. In G. Bünsdorf (Ed.), Applied evolutionary economics, behavior and organizations (Ch. 6, pp. 103–130). Cheltenham: Edward Elgar.

  • Dawid, H., & Neugart, M. (2011). Agent-based models for economic policy design. Eastern Economic Journal, 37, 44–50.

    Article  Google Scholar 

  • Dawid, H., Harting, P., van der Hoog, S., & Neugart, M. (2018a). Macroeconomics with heterogeneous agent models: Fostering transparency, reproducibility and replication. Journal of Evolutionary Economics (forthcoming).

  • Dawid, H., Gemkow, S., Harting, P., van der Hoog, S., & Neugart, M. (2018b). Agent-based macroeconomic modeling and policy analysis: The Eurace@Unibi Model. In S.-H. Chen, M. Kaboudan, & Y.-R. Du (Eds.), The Oxford handbook on computational economics and finance (Ch. 17, pp. 490–519). Oxford: Oxford University Press.

  • Dosi, G., Napoletano, M., Roventini, A., & Treibich, T. (2017). Micro and macro policies in Keynes+Schumpeter evolutionary models. Journal of Evolutionary Economics, 27, 63–90.

    Article  Google Scholar 

  • Duffie, D., & Singleton, K. J. (2003). Credit risk: Pricing, measurement, and management. Princeton: Princeton University Press.

    Google Scholar 

  • Fagiolo, G., & Roventini, A. (2012a). Macroeconomic policy in DSGE and agent-based models. Revue de l’OFCE, 124, 67–116.

    Google Scholar 

  • Fagiolo, G., & Roventini, A. (2012b). On the scientific status of economic policy: A tale of alternative paradigms. The Knowledge Engineering Review, 27, 163–185.

    Article  Google Scholar 

  • Fagiolo, G., Moneta, A., & Windrum, P. (2007). A critical guide to empirical validation of agent-based models in economics: Methodologies, procedures, and open problems. Computational Economics, 30(3), 195–226.

    Article  Google Scholar 

  • Gately, E. (1996). Neural networks for financial forecasting. New York: Wiley.

    Google Scholar 

  • Gorr, W. L. (1994). Editorial: Research prospective on neural network forecasting. International Journal of Forecasting, 10(1), 1–4.

    Article  Google Scholar 

  • Grazzini, J., & Gatti, D. D. (2013). Paper on the development of MABM Mark II: The input–output network in the CRISIS macro agent-based model. CRISIS Project Deliverable D3.3, Universit Cattolica del Sacro Cuore, Milano.

  • Grazzini, J., & Richiardi, M. G. (2013). Consistent estimation of agent-based models by simulated minimum distance. LABORatorio R. Revelli working papers series 130, LABORatorio R. Revelli, Centre for Employment Studies.

  • Grazzini, J., Richiardi, M., & Sella, L. (2012). Indirect estimation of agent-based models: An application to a simple diffusion model. LABORatorio R. Revelli Working papers series 118, LABORatorio R. Revelli, Centre for Employment Studies.

  • Grazzini, J., Richiardi, M. G., & Sella, L. (2013). Analysis of agent-based models. LABORatorio R. Revelli working papers series 135, LABORatorio R. Revelli, Centre for Employment Studies.

  • Harting, P. (2014). Policy design in the presence of technological change: An agent-based approach. Ph.D. Thesis, University of Bielefeld.

  • Hinton, G. E., Osindero, S., & Teh, Y. W. (2006). A fast learning algorithm for deep belief nets. Neural Computing, 18(7), 1527–1554.

    Article  Google Scholar 

  • Hinton, G. E., & Salakhutdinov, R. (2006). Reducing the dimensionality of data with neural networks. Science, 313(5786), 504–507.

    Article  Google Scholar 

  • Hutter, M. (2000). A theory of universal artificial intelligence based on algorithmic complexity. CoRR arXiv:cs.AI/0004001.

  • Kang, S. (1991). An investigation of the use of feedforward neural networks for forecasting. Ph.D. thesis, Kent State University.

  • Kleijnen, J. P. (2015). Design and analysis of simulation experiments. Heidelberg: Springer.

    Book  Google Scholar 

  • Kleijnen, J. P. C. (1995). Verification and validation of simulation models. European Journal of Operational Research, 82(1), 145–162.

    Article  Google Scholar 

  • Kohzadi, N., Boyd, M., Kermanshahi, B., & Kaastra, I. (1996). A comparison of artificial neural network and time series models for forecasting commodity prices. Neurocomputing, 10, 169–181.

    Article  Google Scholar 

  • Kuan, C. M., & Liu, T. (1995). Forecasting exchange rates using feedforward and recurrent neural networks. Journal of Applied Econometrics, 10(4), 347–364.

    Article  Google Scholar 

  • Lamperti, F. (2015). An information theoretic criterion for empirical validation of time series models. LEM papers series 2015/02, Laboratory of Economics and Management (LEM), Sant’Anna School of Advanced Studies, Pisa, Italy.

  • Lamperti, F., Roventini, A., & Sani, A. (2017). Agent-based model calibration using machine learning surrogates. Papers arXiv:1703.10639.

  • Lux, T., & Zwinkels, R. C. J. (2018). Empirical validation of heterogeneous agent models. In C. H. Hommes & B. LeBaron (Eds.), Handbook of computational economics: Heterogeneous agent models (Vol. 4). North Holland: Elsevier.

    Google Scholar 

  • Maasoumi, E., Khotanzad, A., & Abaye, A. (1994). Artificial neural networks for some macroeconomic series: A first report. Econometric Reviews, 13, 105–122.

    Article  Google Scholar 

  • Makridakis, S., Anderson, A., Carbone, R., Fildes, R., Hibdon, M., & Lewandowski, R. (1982). The accuracy of extrapolation (time series) methods: Results of a forecasting competition. Journal of Forecasting, 1, 111–153.

    Article  Google Scholar 

  • Martens, J., & Sutskever, I. (2010). Parallelizable sampling of Markov random fields. In Artificial intelligence and statistics (pp. 517–524).

  • Martens, J., & Sutskever, I. (2011). Learning recurrent neural networks with Hessian-Free optimization. In Proceedings of the 28th International Conference on Machine Learning (ICML), Bellevue, Washington, USA (pp. 1033–1040).

  • Martens, J., & Sutskever, I. (2012). Training deep and recurrent networks with Hessian-Free optimization. In G. Montavon, G. B. Orr, & K. R. Müller (Eds.), Neural networks: Tricks of the trade. Lecture notes in computer science (Vol. 7700, pp. 479–535). Berlin: Springer.

    Chapter  Google Scholar 

  • Nagle, T., & Hogan, J. (2006). The strategy and tactics of pricing: A guide to growing more profitably. Upper Saddle River, NJ: Pearson Prentice Hall.

    Google Scholar 

  • National Physical Laboratory (Ed.). (1959). Mechanisation of thought processes. In Proceedings of a symposium held at the national physical laboratory on the 24th, 25th, 26th and 27th November 1958, Her Majesty’s Stationary Office, 1959.

  • Refenes, A. (1993). Constructive learning and its application to currency exchange rate forecasting, chap 39 (pp. 777–806). Chicago: Probus Publishing Company.

    Google Scholar 

  • Refenes, A. (1995). Neural networks in the capital markets. Chichester: Wiley.

    Google Scholar 

  • Sargent, R. G. (2011). Verification and validation of simulation models. In Proceedings of the winter simulation conference, WSC ’11 (pp. 183–198).

  • Sharda, R. (1994). Neural networks for the ms/or analyst: An application bibliography. Interfaces, 24, 116–130.

    Article  Google Scholar 

  • Simon, H. A. (1955). A behavioral model of rational choice. Quarterly Journal of Economics, 69(1), 99–118.

    Article  Google Scholar 

  • Simon, H. A. (1959). Theories of decision-making in economics and behavioral science. American Economic Review, 49, 253–283.

    Google Scholar 

  • Simon, H. A. (1996 [1969]). The sciences of the artificial (3rd ed.). Cambridge, MA: The MIT Press.

  • Simon, H. A. (1997 [1947]). Administrative behavior (4th ed.). New York, NY: The Free Press.

  • Srinivasan, D., Liew, A., & Chang, C. (1994). A neural network short-term load forecaster. Electric Power Systems Research, 28, 227–234.

    Article  Google Scholar 

  • Sutskever, I. (2013). Training recurrent neural networks. Ph.D. thesis, Department of Computer Science, University of Toronto.

  • Tang, Z., & Fishwick, P. (1993). Feedforward neural nets as models for time series forecasting. ORSA Journal on Computing, 5, 374–385.

    Article  Google Scholar 

  • Tesfatsion, L., & Judd, K. E. (2006). Handbook of computational economics II: Agent-based computational economics. Amsterdam: North-Holland.

    Google Scholar 

  • Trippi, R., & Turban, E. (1993). Neural networks in finance and investment: Using artificial intelligence to improve real-world performance. Chicago: Probus.

    Google Scholar 

  • Weigend, A., & Gershenfeld, N. (1993). Time series prediction: Forecasting the future and understanding the past. Reading, MA: Addison-Wesley.

    Google Scholar 

  • Weigend, A., Huberman, B., & Rumelhart, D. (1992). Predicting sunspots and exchange rates with connectionist networks (pp. 395–432). Redwood City, CA: Addison-Wesley.

    Google Scholar 

  • Werker, C., & Brenner, T. (2004). Empirical calibration of simulation models. Papers on economics and evolution 2004–10, Philipps University Marburg, Department of Geography.

  • Wilson, R., & Sharda, R. (1992). Neural networks. OR/MS Today, pp. 36–42.

  • Yildizoglu, M., & Salle, I. (2012). Efficient sampling and metamodeling for computational economic models. Cahiers du GREThA 2012–18, Groupe de Recherche en Economie Théorique et Appliquée.

Download references


This paper has benefited from discussions with Spyros Kousides, Nan Su and Herbert Dawid. Any remaining errors or omissions are the sole responsibility of the author.

Author information

Authors and Affiliations


Corresponding author

Correspondence to Sander van der Hoog.

Additional information

Financial support from the Horizon 2020 ISIGrowth Project (Innovation-fuelled, Sustainable, Inclusive Growth), under Grant No. 649186, is gratefully acknowledged.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

van der Hoog, S. Surrogate Modelling in (and of) Agent-Based Models: A Prospectus. Comput Econ 53, 1245–1263 (2019).

Download citation

  • Accepted:

  • Published:

  • Issue Date:

  • DOI:


JEL Classification