Stochastically Structured Reservoir Computers for Financial and Economic System Identification

2025/07/23 by Banegas, Lendy, Vides, Fredy
#FOS: Economics and business #FOS: Electrical engineering #FOS: Mathematics #Optimization and Control (math.OC) #Systems and Control (eess.SY) #Theoretical Economics (econ.TH) #electronic engineering #information engineering

paper · doi:10.48550/arxiv.2507.17115

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.

Citations

• Dynamic financial processes identification using sparse regressive reservoir computers
• Measuring the Effectiveness of US Monetary Policy during the COVID-19 Recession
• Random Projections for the Nonnegative Least-Squares Problem

Related

• Dynamic financial processes identification using sparse regressive reservoir computers
• High-Dimensional Dynamic Stochastic Model Representation
• Reservoir Computing with Error Correction: Long-term Behaviors of Stochastic Dynamical Systems
• Dynamics of reservoir computing for crises prediction
• Nonlinear Autoregression with Convergent Dynamics on Novel Computational Platforms