Agent-based model calibration using machine learning surrogates

Abstract

Taking agent-based models (ABM) closer to the data is an open challenge. This paper explicitly tackles parameter space exploration and calibration of ABMs combining supervised machine-learning and intelligent sampling to build a surrogate meta-model. The proposed approach provides a fast and accurate approximation of model behaviour, dramatically reducing computation time. In that, our machine-learning surrogate facilitates large scale explorations of the parameter-space, while providing a powerful filter to gain insights into the complex functioning of agent-based models. The algorithm introduced in this paper merges model simulation and output analysis into a surrogate meta-model, which substantially ease ABM calibration. We successfully apply our approach to the Brock and Hommes (1998) asset pricing model and to the "Island" endogenous growth model (Fagiolo and Dosi, 2003). Performance is evaluated against a relatively large outof-sample set of parameter combinations, while employing different user-defined statistical tests for output analysis. The results demonstrate the capacity of machine learning surrogates to facilitate fast and precise exploration of agent-based models' behaviour over their often rugged parameter spaces. KEY WORDSAgent based model; calibration; machine learning; surrogate; meta-model. JELC15, C52, C63.

Faraway, So Close: Coupled Climate and Economic Dynamics in an Agent-based Integrated Assessment Model

“…Notice that alternative approaches for large scale models are under development. SeeBarde (2016);Lamperti (2017Lamperti ( , 2016;Lamperti et al (2017);Guerini and Moneta (2016).43 These feedbacks have been calibrated according toSterman et al (2013) and C-ROADS model documentation. See https: //www.climateinteractive.org/tools/c-roads/technical.…”

More is different ... and complex! the case for agent-based macroeconomics

“…No matter the empirical validation procedures actually employed, an important domain of analysis regards the sensitivity of the model to parameter changes, through different methods including Kriging meta-modeling (Salle and Yıldızoglu, 2014;Bargigli et al, 2016;Dosi et al, 2017dDosi et al, ,c, 2018c, and machine-learning surrogates (Lamperti et al, 2018c). Such methodologies provide detailed sensitivity analyses of macro ABMs, allowing one to get a quite deep descriptive knowledge of the behavior of the system.…”

Policy Modeling and Applications: State-of-the-Art and Perspectives

“…Advances in the area have been so intertwining that new models have started to feed from different trends of spatial-modeling literature bridging transportation and landuse models to macroeconomics [82] and actual life-cycle of individuals in order to generate individual demand models [83]. The bridge has also been generous when crossing automated computing techniques and traditional models [84] or when aiding its validation [85].…”