2017/11 LEM Working Paper Series

Agent-Based Model Calibration using Machine Learning Surrogates

Francesco Lamperti, Andrea Roventini and Amir Sani
  Keywords
 
agent based model; calibration; machine learning; surrogate; meta-model


  JEL Classifications
 
C15, C52, C63


  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.
  Downloads
 
download pdf


Back