AI-INTELLIGENCE DRIVEN MONETARY POLICY OPTIMIZATION IN CBDC ECONOMIES-PAPER ON ADJUSTED INTEREST RATE FOR PROGRAMMABLE MONEY: AN EMERGING FRAMEWORK FOR ALGORITHMIC MONETARY POLICY

Abstract

Programmable money—digital currency whose behaviour is controlled by code—creates new design space for dynamic, data-driven monetary policy. This paper proposes a framework for AI-adjusted interest rates in programmable monetary systems, w here machine-learning models continuously calibrate interest-rate parameters in response to real-time economic and network conditions. We formally describe the architecture of such systems, illustrate how AI-driven mechanisms can extend existing algorithmic interest-rate models in decentralized finance (DeFi), and discuss their potential integration with central bank digital currencies (CBDCs). Using stylized simulation data calibrated to typical DeFi lending dynamics, we compare baseline algorithmic rate m odels with an AI-adjusted variant, showing reduced volatility and smoother utilization patterns. A case study on Compound and Aave interest-rate mechanisms demonstrates how AI- based forecasting and reinforcement learning could enhance stability and policy precision. We conclude by outlining governance, regulatory, and ethical considerations, and propose a research agenda for AI-driven algorithmic monetary policy.