Deep Learning in Agent-Based Models: A Prospectus

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. (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 Deep Learning and multi-layered neural networks to agent-based models in economics.

[1]  Paul A. Fishwick,et al.  Feedforward Neural Nets as Models for Time Series Forecasting , 1993, INFORMS J. Comput..

[2]  Agent-Based Models of Organizations Handbook of Computational Economics II : Agent-Based Computational Economics , 2005 .

[3]  Thomas Brenner,et al.  Empirical Calibration of Simulation Models , 2004 .

[4]  A. C. Liew,et al.  A neural network short-term load forecaster , 1994 .

[5]  D. Signorini,et al.  Neural networks , 1995, The Lancet.

[6]  Suh Young Kang,et al.  An investigation of the use of feedforward neural networks for forecasting , 1992 .

[7]  Ilya Sutskever,et al.  Parallelizable Sampling of Markov Random Fields , 2010, AISTATS.

[8]  D. Rumelhart,et al.  Predicting sunspots and exchange rates with connectionist networks , 1991 .

[9]  Andreas S. Weigend,et al.  Time Series Prediction: Forecasting the Future and Understanding the Past , 1994 .

[10]  Chung-Ming Kuan,et al.  Forecasting exchange rates using feedforward and recurrent neural networks , 1992 .

[11]  Mohamed Chtourou,et al.  On the training of recurrent neural networks , 2011, Eighth International Multi-Conference on Systems, Signals & Devices.

[12]  H. Simon,et al.  Theories of Decision-Making in Economics and Behavioural Science , 1966 .

[13]  G. Dosi,et al.  Schumpeter meeting Keynes: A policy-friendly model of endogenous growth and business cycles , 2010 .

[14]  Robert L. Winkler,et al.  The accuracy of extrapolation (time series) methods: Results of a forecasting competition , 1982 .

[15]  G. Fagiolo,et al.  Agent-based models for economic policy design: Introduction to the special issue , 2008 .

[16]  Sylvain Barde,et al.  A Practical, Universal, Information Criterion over Nth Order Markov Processes , 2015 .

[17]  Ilya Sutskever,et al.  Learning Recurrent Neural Networks with Hessian-Free Optimization , 2011, ICML.

[18]  Philipp Harting,et al.  Policy design in the presence of technological change - an agent-based approach , 2014 .

[19]  Markus Raab,et al.  Theories of Decision Making , 2011 .

[20]  Ilya Sutskever,et al.  Training Deep and Recurrent Networks with Hessian-Free Optimization , 2012, Neural Networks: Tricks of the Trade.

[21]  H. Simon,et al.  A Behavioral Model of Rational Choice , 1955 .

[22]  Ramesh Sharda,et al.  Neural Networks for the MS/OR Analyst: An Application Bibliography , 1994 .

[23]  Nowrouz Kohzadi,et al.  A comparison of artificial neural network and time series models for forecasting commodity prices , 1996, Neurocomputing.

[24]  Mauro Gallegati,et al.  Modeling Maximum Entropy and Mean-Field Interaction in Macroeconomics , 2008 .

[25]  Steven N. Durlauf,et al.  The Economy As an Evolving Complex System III: Current Perspectives and Future Directions , 2005 .

[26]  Geoffrey E. Hinton,et al.  Reducing the Dimensionality of Data with Neural Networks , 2006, Science.

[27]  Razvan Pascanu,et al.  Advances in optimizing recurrent networks , 2012, 2013 IEEE International Conference on Acoustics, Speech and Signal Processing.

[28]  E. Michael Azoff,et al.  Neural Network Time Series: Forecasting of Financial Markets , 1994 .

[29]  Herbert Dawid,et al.  Capturing Firm Behavior in Agent-based Models of Industry Evolution and Macroeconomic Dynamics , 2012 .

[30]  Siew Lan Loo.  Neural networks for financial forecasting , 1994 .

[31]  H. Bacha,et al.  A neural network architecture for load forecasting , 1992, [Proceedings 1992] IJCNN International Joint Conference on Neural Networks.

[32]  Yee Whye Teh,et al.  A Fast Learning Algorithm for Deep Belief Nets , 2006, Neural Computation.

[33]  Thomas Brenner,et al.  A Practical Guide to Inference in Simulation Models , 2006 .

[34]  Linda Argote,et al.  A Behavioral Theory of the Firm - 40 Years and Counting: Introduction and Impact , 2007, Organ. Sci..

[35]  Joshua M. Epstein,et al.  Growing Artificial Societies: Social Science from the Bottom Up , 1996 .

[36]  Giovanni Dosi,et al.  Micro and macro policies in the Keynes+Schumpeter evolutionary models , 2014, Journal of Evolutionary Economics.

[37]  M. Shubik,et al.  A Behavioral Theory of the Firm. , 1964 .

[38]  F. Lamperti.  An Information Theoretic Criterion for Empirical Validation of Time Series Models , 2015 .

[39]  Georges Dionne,et al.  Credit Risk: Pricing, Measurement, and Management , 2005 .

[40]  T. Lux,et al.  Estimation of Agent-Based Models: The Case of an Asymmetric Herding Model , 2005 .

[41]  Herbert A. Simon,et al.  The Sciences of the Artificial , 1970 .

[42]  Thomas T. Nagle,et al.  The Strategy and Tactics of Pricing: A Guide to Growing More Profitably , 2005 .

[43]  Sebastiano Manzan,et al.  Behavioral Heterogeneity in Stock Prices , 2005 .

[44]  G. Fagiolo,et al.  Macroeconomic Policy in DSGE and Agent-Based Models Redux: New Developments and Challenges Ahead , 2012, J. Artif. Soc. Soc. Simul..

[45]  G. Dosi,et al.  Income Distribution, Credit and Fiscal Policies in an Agent-Based Keynesian Model , 2012 .

[46]  A. Refenes.  Neural Networks in the Capital Markets , 1994 .

[47]  Jack P. C. Kleijnen,et al.  EUROPEAN JOURNAL OF OPERATIONAL , 1992 .

[48]  Efraim Turban,et al.  Neural Networks in Finance and Investing: Using Artificial Intelligence to Improve Real-World Performance , 1992 .

[49]  Matteo Richiardi,et al.  Consistent Estimation of Agent-Based Models by Simulated Minimum Distance , 2013 .

[50]  Esfandiar Maasoumi,et al.  Artificial neural networks for some macroeconomic series: A first report , 1994 .

[51]  Giorgio Fagiolo,et al.  On the scientific status of economic policy: a tale of alternative paradigms* , 2012, The Knowledge Engineering Review.

[52]  Wilpen L. Gorr,et al.  Editorial: Research prospective on neural network forecasting , 1994 .

[53]  Paul Windrum,et al.  A Critical Guide to Empirical Validation of Agent-Based Models in Economics: Methodologies, Procedures, and Open Problems , 2007 .

[54]  Herbert Dawid,et al.  Agent-Based Macroeconomic Modeling and Policy Analysis: The Eurace@Unibi Model , 2014 .

[55]  Isabelle Salle,et al.  Efficient Sampling and Metamodeling for Computational Economic Models , 2012 .

[56]  Matteo Richiardi,et al.  Analysis of Agent-based Models , 2013 .

[57]  Geoffrey E. Hinton,et al.  Training Recurrent Neural Networks , 2013 .

[58]  Herbert Dawid,et al.  Agent-based Models for Economic Policy Design , 2011 .

[59]  Matteo Richiardi,et al.  Indirect estimation of agent-based models.An application to a simple diffusion model , 2013 .