Calibrating the Mean-Reversion Parameter in the Hull-White Model Using Neural Networks

Abstract

Interest rate models are widely used for simulations of interest rate movements and pricing of interest rate derivatives. We focus on the Hull-White model, for which we develop a technique for calibrating the speed of mean reversion. We examine the theoretical time-dependent version of mean reversion function and propose a neural network approach to perform the calibration based solely on historical interest rate data. The experiments indicate the suitability of depth-wise convolution and provide evidence for the advantages of neural network approach over existing methodologies. The proposed models produce mean reversion comparable to rolling-window linear regression’s results, allowing for greater flexibility while being less sensitive to market turbulence.