Neural Network-Based Parameter Estimation of a Labour Market Agent-Based Model

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Alves, M Lopes, Dyer, Joel, Farmer, Doyne, Wooldridge, Michael, Calinescu, Anisoara
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866908867810557952
author Alves, M Lopes
Dyer, Joel
Farmer, Doyne
Wooldridge, Michael
Calinescu, Anisoara
author_facet Alves, M Lopes
Dyer, Joel
Farmer, Doyne
Wooldridge, Michael
Calinescu, Anisoara
contents Agent-based modelling (ABM) is a widespread approach to simulate complex systems. Advancements in computational processing and storage have facilitated the adoption of ABMs across many fields; however, ABMs face challenges that limit their use as decision-support tools. A significant issue is parameter estimation in large-scale ABMs, particularly due to computational constraints on exploring the parameter space. This study evaluates a state-of-the-art simulation-based inference (SBI) framework that uses neural networks (NN) for parameter estimation. This framework is applied to an established labour market ABM based on job transition networks. The ABM is initiated with synthetic datasets and the real U.S. labour market. Next, we compare the effectiveness of summary statistics derived from a list of statistical measures with that learned by an embedded NN. The results demonstrate that the NN-based approach recovers the original parameters when evaluating posterior distributions across various dataset scales and improves efficiency compared to traditional Bayesian methods.
format Preprint
id arxiv_https___arxiv_org_abs_2602_15572
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Neural Network-Based Parameter Estimation of a Labour Market Agent-Based Model
Alves, M Lopes
Dyer, Joel
Farmer, Doyne
Wooldridge, Michael
Calinescu, Anisoara
Machine Learning
Multiagent Systems
Agent-based modelling (ABM) is a widespread approach to simulate complex systems. Advancements in computational processing and storage have facilitated the adoption of ABMs across many fields; however, ABMs face challenges that limit their use as decision-support tools. A significant issue is parameter estimation in large-scale ABMs, particularly due to computational constraints on exploring the parameter space. This study evaluates a state-of-the-art simulation-based inference (SBI) framework that uses neural networks (NN) for parameter estimation. This framework is applied to an established labour market ABM based on job transition networks. The ABM is initiated with synthetic datasets and the real U.S. labour market. Next, we compare the effectiveness of summary statistics derived from a list of statistical measures with that learned by an embedded NN. The results demonstrate that the NN-based approach recovers the original parameters when evaluating posterior distributions across various dataset scales and improves efficiency compared to traditional Bayesian methods.
title Neural Network-Based Parameter Estimation of a Labour Market Agent-Based Model
topic Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2602.15572