Optimal risk-aware interest rates for decentralized lending protocols

Interest rates in decentralized lending protocols are set algorithmically and adjust to supply and demand for liquidity. In this study, we propose an optimal interest rate model that maximizes the expected lender wealth while incorporating penalties for liquidity risk and interest rate stabilization. This objective benefits both sides of the market: it improves yield and reduces liquidity risk for lenders, while encouraging borrower activity indirectly through higher utilization and directly through stabilized borrowing costs. The dynamics of the utilization rate are modeled using point processes whose intensities depend on the interest rate. When intensities are linear, the optimal interest rate model is derived from a system of Riccati-type ODEs. In the nonlinear case, we approximate it using a Monte-Carlo estimator coupled with deep learning techniques. Finally, using block-by-block data, we conduct a risk-adjusted profit and loss analysis to compare industry-standard interest rate models to the deep learning-based one.