Stochastically Structured Reservoir Computers for Financial and Economic System Identification

TL;DR

This paper presents a novel methodology using stochastically structured reservoir computers to identify and simulate complex financial and economic systems, improving interpretability and modeling accuracy under uncertainty.

Contribution

It introduces a new SSRC framework combining structure-preserving embeddings with graph-informed coupling matrices for better system modeling and interpretability.

Findings

Successfully modeled nonlinear stochastic dynamics

Captured complex inter-agent relationships

Enabled interpretable economic predictions

Abstract

This paper introduces a methodology for identifying and simulating financial and economic systems using stochastically structured reservoir computers (SSRCs). The framework combines structure-preserving embeddings with graph-informed coupling matrices to model inter-agent dynamics while enhancing interpretability. A constrained optimization scheme guarantees compliance with both stochastic and structural constraints. Two empirical case studies, a nonlinear stochastic dynamic model and regional inflation network dynamics, demonstrate the effectiveness of the approach in capturing complex nonlinear patterns and enabling interpretable predictive analysis under uncertainty.