Moment set selection for the SMM using simple machine learning

0574253 - ÚTIA 2024 RIV NL eng J - Journal Article
Žíla, Eric - Kukačka, Jiří
Moment set selection for the SMM using simple machine learning.
Journal of Economic Behavior & Organization. Roč. 212, č. 1 (2023), s. 366-391. ISSN 0167-2681. E-ISSN 1879-1751
R&D Projects: GA ČR GA20-14817S
Institutional support: RVO:67985556
Keywords : Agent-based model * Machine learning * Simulated method of moments * Stepwise selection
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)
Impact factor: 2.2, year: 2022
Method of publishing: Limited access
http://library.utia.cas.cz/separaty/2023/E/kukacka-0574253.pdf https://www.sciencedirect.com/science/article/pii/S0167268123001944?via%3Dihub

This paper addresses the moment selection issue of the simulated method of moments, an estimation technique commonly applied to intractable agent-based models. We develop a simple machine learning extension reducing arbitrariness and automating the moment choice. Two algorithms are proposed: backward stepwise moment elimination and forward stepwise moment selection. The methodology is tested using simulations on a Markov-switching multifractal framework and two popular financial agent-based models with increasing complexity. We find that both algorithms can identify multiple moment sets that outperform all benchmark sets. Moreover, we achieve considerable in-sample estimation precision gains of up to 66 percent for agent-based models. Finally, an out-of-sample empirical exercise with S&P 500 data strongly supports the practical applicability of our methodology as the estimated models pass the validity test of overidentifying restrictions.
Permanent Link: https://hdl.handle.net/11104/0344591