A differentiable model of supply-chain shocks
This enables scaling ABMs to model the entire global supply network, addressing a critical problem in economics for policymakers and researchers.
The paper tackled the challenge of calibrating agent-based models (ABMs) for supply-chain shock propagation by using GPUs and automatic differentiation, achieving speed-ups of over 3 orders of magnitude compared to non-differentiable baselines.
Modelling how shocks propagate in supply chains is an increasingly important challenge in economics. Its relevance has been highlighted in recent years by events such as Covid-19 and the Russian invasion of Ukraine. Agent-based models (ABMs) are a promising approach for this problem. However, calibrating them is hard. We show empirically that it is possible to achieve speed ups of over 3 orders of magnitude when calibrating ABMs of supply networks by running them on GPUs and using automatic differentiation, compared to non-differentiable baselines. This opens the door to scaling ABMs to model the whole global supply network.