Dynamic Interest Rate Discovery in Decentralized Finance Reverse Kelly Automated Market Maker for Risk-Adjusted Lending

Jul 16, 2026

Upload by Violet

Decentralized Finance (DeFi) lending protocols typically use heuristic, utilization-based bonding curves that force severe over-collateralization and systematically exclude under-collateralized assets such as corporate invoices. This paper presents Reverse Kelly Automated Market Maker (rkAMM), a mathematically optimal pricing engine for decentralized credit. By inverting the Kelly Criterion, rkAMM dynamically prices individual loan risk from real-time Probability of Default streams to achieve target LP yields, proving strictly convex superiority over Aave and Compound’s static curves.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages21

Reading Time53 min

Abstract

Introduction

Objectives and Contributions

arXiv :2607 .04 178v 1 [ cs . SI ] 5 Jul 2026 Dynamic Interest Rate Discovery in Decentralized Finance: AReverse Kelly Automated Market Maker for Risk-Adjusted Lending Sai Srikanth Madugula∗1, Peplluis Esteva de la Rosa†2, and Daya Shankar‡3 1 School of Technology, Woxsen University, Hyderabad, Telangana 502345, India 2 Universitat de Girona, 17004 Girona, Spain 3 School of Sciences, Woxsen University, Hyderabad, Telangana 502345, India July 7, 2026 Abstract Decentralized Finance (DeFi) lending protocols currently rely on heuristic, utilization-based bonding curves that mandate severe over-collateralization, systematically excluding under-collateralized assets like corporate invoices. This paper introduces a mathematically optimal pricing mechanism for decentralized credit: the Reverse Kelly Automated Market Maker (rkAMM), the core engine of our proposed lending framework. By inverting the Kelly Criterion, traditionally used for optimal bet sizing, we construct a dynamic interest rate discovery protocol that explicitly prices individual loan risk. The rkAMM ingests real-time Probability of Default (PD) streams from an off-chain Explainable AI oracle and dynamically calculates the exact interest rate required to sustain target liquidity provider (LP) yields. We mathematically derive the Reverse Kelly pricing function (r = y1PDPD), proving its strictly convex superiority over Aave and Compound’s static utilization curves in managing capital efficiency. Furthermore, we deploy the rkAMM architecture via Solidity smart contracts, optimizing for gas-efficient 1e18 (WAD) floating-point arithmetic. To ensure decentralized transparency, our simulation infrastructure leverages MLflow for tracking yield hyperparameters, Data Version Control (DVC) linked to DagsHub for versioning Real-World Asset (RWA) data arrays, and localized edge-inference via Ollama (Llama-3) and Hugging Face (FinBERT) for zero-cost predictive modeling. Monte Carlo simulations across 10,000 macroeconomic stress scenarios confirm that the rkAMM maintains protocol solvency and stabilizes LP yields at 12-15% net of expected credit losses. This work provides the foundational financial engineering required to bridge the $2 trillion global supply chain finance gap using permissionless blockchain infrastructure. Keywords: Automated Market Makers, Kelly Criterion, Decentralized Finance, Smart Contracts, Dynamic Pricing, Credit Risk, Real-World Assets, Machine Learning ∗ Corresponding Author. Email: saisrikanth.madugula [phd.2023@woxsen.edu.in](phd.2023@woxsen.edu.in)—ORCID: 0000-0001-6479-8443 †[Email: joseplluis.delarosa@udg.edu](Email: joseplluis.delarosa@udg.edu)—ORCID: 0000-0003-1412-4170 ‡Email: [daya.shankar@woxsen.edu.in](daya.shankar@woxsen.edu.in) 1 Introduction The rapid proliferation of Decentralized Finance (DeFi) has revolutionized peer-to-peer capital allocation, growing into a multi-billion dollar ecosystem (Werner et al. , 2022; Harvey et al. , 2021; Schar, 2021; Nakamoto, 2008; Buterin, 2014) . However, the dominant lending protocols in this space, most notably Aave and Compound, rely on architectural primitives that severely limit their utility for real-world economic activity (Gudgeon et al. , 2020a; Perez et al. , 2021; Gudgeon et al. , 2020b) . These protocols utilize heuristic, piecewise-linear utilization curves to determine interest rates. Consequently, risk is managed not through precise algorithmic pricing, but through blunt over-collateralization, frequently requiring borrowers to post 150% to 200% of the loan value in highly liquid digital assets (Xu et al. , 2022; Tolmach et al. , 2021) . While this model successfully secures protocol solvency against crypto-asset volatility (Qin et al. , 2021a; Klages-Mundt et al. , 2020), it is fundamentally incompatible with traditional supply chain finance and Small and Medium-sized Enterprise (SME) lending (Chen et al. , 2022; Meyer et al. , 2022) . In these markets, credit is e

FAQs

Why do current DeFi lending protocols require heavy over-collateralization?

They rely on heuristic utilization-based bonding curves that protect solvency but do not provide precise algorithmic risk pricing. As a result, borrowers often must post 150% to 200% collateral in liquid crypto assets.

What is the Reverse Kelly Automated Market Maker (rkAMM)?

rkAMM is a dynamic interest rate discovery mechanism that inverts the Kelly Criterion to translate risk scores into exact, solvent interest rates. It is designed to sustain target liquidity provider yields while pricing individual loan risk.

How does rkAMM obtain risk information to set interest rates?

rkAMM ingests real-time Probability of Default (PD) streams from an off-chain Explainable AI oracle. These PD inputs drive the Reverse Kelly pricing function and the resulting interest rate calculations.

Jul 16, 2026

Upload by Violet